Gjenerimi i imazhit Nano Banana
Gjeneruar nga Nano Banana 2 Pyetje: "Një foto e një kopertine me shkëlqim reviste, kopertina minimale blu ka fjalët e mëdha të trasha Nano Banana. Teksti është me shkronja serif dhe mbush pamjen. Asnjë tekst tjetër. Përpara tekstit ka një portret të një personi me një fustan elegant dhe minimalist. Ajo mban me shaka numrin 2, i cili është pika qendrore."
Vendos numrin e botimit dhe datën "Shkurt 2026" në cep së bashku me një barkod. Revista është në një raft pranë një muri të suvatuar me portokalli, brenda një dyqani firmash.Gjeneruar nga Nano Banana Pro Nxitje: "Paraqitni një skenë të qartë, 45° nga lart poshtë, vizatimore 3D miniaturë izometrike të Londrës, duke paraqitur monumentet dhe elementët e saj arkitektonikë më ikonikë. Përdorni tekstura të buta dhe të rafinuara me materiale realiste PBR dhe ndriçim dhe hije të buta dhe të gjalla. Integroni kushtet aktuale të motit direkt në mjedisin e qytetit për të krijuar një atmosferë atmosferike gjithëpërfshirëse. Përdorni një kompozim të pastër dhe minimalist me një sfond të butë me ngjyra të forta. Në qendër të sipërme, vendosni titullin "Londër" me tekst të madh të trashë, një ikonë të spikatur moti poshtë tij, pastaj datën (tekst i vogël) dhe temperaturën (tekst mesatar). I gjithë teksti duhet të jetë i qendërzuar me hapësira të qëndrueshme dhe mund të mbivendoset lehtë me majat e ndërtesave."Gjeneruar nga Nano Banana 2 Njoftim: "Përdorni kërkimin e imazheve për të gjetur imazhe të sakta të një zogu të shkëlqyer ketzal. Krijoni një sfond të bukur 3:2 të këtij zogu, me një gradient natyral nga lart poshtë dhe kompozim minimal."
Gjeneruar nga Nano Banana Pro Nxitje: "Vendoseni këtë logo në një reklamë luksoze për një parfum me aromë bananeje. Logoja është integruar në mënyrë të përkryer në shishe."Gjeneruar nga Nano Banana Pro Njoftim: "Një foto e një skene të përditshme në një kafene të mbushur me njerëz që shërben mëngjes. Në plan të parë është një burrë anime me flokë blu, njëri prej personave është një skicues me laps, një tjetër është një person që punon me argjilë"Gjeneruar nga Nano Banana Pro Njoftim: "Përdorni kërkimin për të gjetur se si është pritur lançimi i Gemini 3 Flash. Përdorni këtë informacion për të shkruar një artikull të shkurtër rreth tij (me tituj). Ktheni një foto të artikullit ashtu siç u shfaq në një revistë me shkëlqim të fokusuar në dizajn. Është një foto e një faqeje të vetme të palosur, që tregon artikullin rreth Gemini 3 Flash. Një foto kryesore. Titulli është me serif."Gjeneruar nga Nano Banana Pro Njoftim: "Një ikonë që përfaqëson një qen të lezetshëm. Sfondi është i bardhë. Krijoni ikonat në një stil 3D shumëngjyrësh dhe të prekshëm. Pa tekst."Gjeneruar nga Nano Banana 2 Nxitje: "Bëni një foto që është në mënyrë perfekte izometrike. Nuk është një miniaturë, është një foto e kapur që rastësisht është në mënyrë perfekte izometrike. Është një foto e një kopshti të bukur modern. Ka një pishinë të madhe në formë 2 dhe fjalët: Nano Banana 2."
Nano Banana është emri për aftësitë e gjenerimit të imazheve native të Gemini. Gemini mund të gjenerojë dhe përpunojë imazhe në mënyrë bisedore me tekst, imazhe, video ose një kombinim. Kjo ju lejon të krijoni, modifikoni dhe përsërisni pamjet me një kontroll të paparë.
Nano Banana i referohet katër modeleve të dallueshme të disponueshme në Gemini API:
- Nano Banana 2 Lite ( Gemini 3.1 Flash Lite Image ) (
gemini-3.1-flash-lite-image): Modeli ynë më i shpejtë dhe më i lirë i imazhit Gemini, i projektuar për shpejtësi dhe shkallë ku shpejtësia dhe kostoja janë kufizimet kryesore operative. Nuk është optimizuar për hyrje të shumëfishta referimi ose redaktim sekuencial me shumë kthesa. - Nano Banana 2 ( Gemini 3.1 Flash Image ) (
gemini-3.1-flash-image): Shërben si modeli më i gjithanshëm, modeli më i fuqishëm për të gjitha detyrat. Ai balancon shpejtësinë me gjenerimin e teknologjisë së fundit 4K, njohuritë botërore dhe interpretimin e besueshëm të tekstit. Shkëlqyeshëm në përpunimin dhe qëndrueshmërinë e imazheve me referencë të shumëfishtë. - Nano Banana Pro ( Gemini 3 Pro Image ) (
gemini-3-pro-image): Zgjedhja premium për detyrat më komplekse vizuale, duke ofruar nivelin më të lartë të njohurive botërore, lokalizim të përparuar, qëndrueshmëri të saktë të markës dhe kontroll krijues preciz. - Nano Banana ( Gemini 2.5 Flash Image ) (
gemini-2.5-flash-image): Pionieri i trashëguar i serisë Nano Banana. Ndërsa ka qenë një kalë pune i besueshëm, ne u rekomandojmë fuqimisht klientëve të kalojnë në Nano Banana 2 Lite për të përjetuar cilësi të përmirësuar, shpejtësi më të larta gjenerimi dhe çmime më të ulëta të API-t.
Të gjitha imazhet e gjeneruara përfshijnë një filigran SynthID .
Gjenerimi i imazhit (tekst-në-imazh)
Python
from google import genai
from PIL import Image
import base64
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input="Create a picture of a nano banana dish in a fancy restaurant with a Gemini theme",
)
with open("generated_image.png", "wb") as f:
f.write(base64.b64decode(interaction.output_image.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const prompt =
"Create a picture of a nano banana dish in a fancy restaurant with a Gemini theme";
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: prompt,
});
const generatedImage = interaction.output_image;
if (generatedImage) {
const buffer = Buffer.from(generatedImage.data, "base64");
fs.writeFileSync("gemini-native-image.png", buffer);
console.log("Image saved as gemini-native-image.png");
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("base64"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": [
{"type": "text", "text": "Create a picture of a nano banana dish in a fancy restaurant with a Gemini theme"}
]
}'
Mund të merrni të dhënat e gjeneruara të imazhit duke përdorur vetinë interaction.output_image , e cila kthen bllokun e fundit të gjeneruar të imazhit. Për detaje mbi vetitë e komoditetit, shihni përmbledhjen e Ndërveprimeve .
Redaktimi i imazhit (tekst dhe imazh në imazh)
Kujtesë : Sigurohuni që keni të drejtat e nevojshme për çdo imazh që ngarkoni. Mos gjeneroni përmbajtje që shkel të drejtat e të tjerëve, duke përfshirë video ose imazhe që mashtrojnë, ngacmojnë ose dëmtojnë. Përdorimi juaj i këtij shërbimi gjenerues të IA-së i nënshtrohet Politikës sonë të Përdorimit të Ndaluar .
Jepni një imazh dhe përdorni udhëzime tekstuale për të shtuar, hequr ose modifikuar elementë, për të ndryshuar stilin ose për të rregulluar gradimin e ngjyrave.
Shembulli i mëposhtëm demonstron ngarkimin e imazheve të koduara base64 . Për imazhe të shumëfishta, ngarkesa më të mëdha dhe lloje MIME të mbështetura, kontrolloni faqen Kuptimi i imazheve .
Python
from google import genai
from PIL import Image
import base64
client = genai.Client()
with open("/path/to/cat_image.png", "rb") as f:
image_bytes = f.read()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=[
{
"type": "text",
"text": "Create a picture of a nano banana dish in a fancy restaurant with a Gemini theme"
},
{
"type": "image",
"data": base64.b64encode(image_bytes).decode('utf-8'),
"mime_type": "image/png"
}
],
)
with open("generated_image.png", "wb") as f:
f.write(base64.b64decode(interaction.output_image.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const imagePath = "path/to/cat_image.png";
const imageData = fs.readFileSync(imagePath);
const base64Image = imageData.toString("base64");
const prompt = [
{ type: "text", text: "Create a picture of my cat eating a nano-banana in a" +
"fancy restaurant under the Gemini constellation" },
{
type: "image",
mime_type: "image/png",
data: base64Image
},
];
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: prompt,
});
const generatedImage = interaction.output_image;
if (generatedImage) {
const buffer = Buffer.from(generatedImage.data, "base64");
fs.writeFileSync("gemini-native-image.png", buffer);
console.log("Image saved as gemini-native-image.png");
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Create a picture of my cat eating a nano-banana in a"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d "{
\"model\": \"gemini-3.1-flash-image\",
\"input\": [
{\"type\": \"text\", \"text\": \"Create a picture of my cat eating a nano-banana in a fancy restaurant under the Gemini constellation\"},
{
\"type\": \"image\",
\"mime_type\": \"image/jpeg\",
\"data\": \"<BASE64_IMAGE_DATA>\"
}
]
}"
Redaktimi i imazhit me shumë kthesa
Vazhdo të gjenerosh dhe modifikosh imazhe në mënyrë bisedore. Biseda me shumë kthesa është mënyra e rekomanduar për të përsëritur imazhet. Shembulli i mëposhtëm tregon një sugjerim për të gjeneruar një infografik rreth fotosintezës.
Python
from google import genai
import base64
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input="Create a vibrant infographic that explains photosynthesis as if it were a recipe for a plant's favorite food. Show the \"ingredients\" (sunlight, water, CO2) and the \"finished dish\" (sugar/energy). The style should be like a page from a colorful kids' cookbook, suitable for a 4th grader.",
tools=[{"type": "google_search"}],
)
with open("photosynthesis.png", "wb") as f:
f.write(base64.b64decode(interaction.output_image.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
const ai = new GoogleGenAI({});
async function main() {
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "Create a vibrant infographic that explains photosynthesis as if it were a recipe for a plant's favorite food. Show the \"ingredients\" (sunlight, water, CO2) and the \"finished dish\" (sugar/energy). The style should be like a page from a colorful kids' cookbook, suitable for a 4th grader.",
tools: [{"type": "google_search"}],
});
const generatedImage = interaction.output_image;
if (generatedImage) {
const buffer = Buffer.from(generatedImage.data, "base64");
fs.writeFileSync("photosynthesis.png", buffer);
console.log("Image saved as photosynthesis.png");
}
}
await main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Create a vibrant infographic that explains photosynthesis as if it were a recipe for a plant"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": [
{"type": "text", "text": "Create a vibrant infographic that explains photosynthesis as if it were a recipe for a plants favorite food. Show the \"ingredients\" (sunlight, water, CO2) and the \"finished dish\" (sugar/energy). The style should be like a page from a colorful kids cookbook, suitable for a 4th grader."}
],
"tools": [{"type": "google_search"}]
}'
Pastaj mund të përdorni previous_interaction_id për të ndryshuar gjuhën në grafik në spanjisht.
Python
interaction_2 = client.interactions.create(
model="gemini-3.1-flash-image",
input="Update this infographic to be in Spanish. Do not change any other elements of the image.",
previous_interaction_id=interaction.id,
response_format={
"type": "image",
"mime_type": "image/jpeg",
"aspect_ratio": "16:9",
"image_size": "2K"
},
)
generated_image = interaction_2.output_image
if generated_image:
with open("photosynthesis_spanish.png", "wb") as f:
f.write(base64.b64decode(generated_image.data))
JavaScript
const interaction2 = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "Update this infographic to be in Spanish. Do not change any other elements of the image.",
previous_interaction_id: interaction.id,
response_format: {
type: "image",
mime_type: "image/png",
aspect_ratio: "16:9",
image_size: "2K"
},
});
const generatedImage = interaction2.output_image;
if (generatedImage) {
const buffer = Buffer.from(generatedImage.data, "base64");
fs.writeFileSync("photosynthesis_spanish.png", buffer);
}
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Update this infographic to be in Spanish. Do not change any other elements of the image."))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "gemini-3.1-flash-image",
"input": "Update this infographic to be in Spanish. Do not change any other elements of the image.",
"previous_interaction_id": "<PREVIOUS_INTERACTION_ID>",
"response_format": {
"type": "image",
"mime_type": "image/jpeg",
"aspect_ratio": "16:9",
"image_size": "2K"
}
}'
E re me modelet e imazhit Gemini 3
Gemini 3 ofron modele të gjenerimit dhe redaktimit të imazheve të teknologjisë së fundit. Gemini 3.1 Flash Image është i optimizuar për shpejtësi dhe raste përdorimi me volum të lartë, dhe Gemini 3 Pro Image është i optimizuar për prodhimin profesional të aseteve. I projektuar për të përballuar rrjedhat më sfiduese të punës përmes arsyetimit të avancuar, ato shkëlqejnë në detyra komplekse krijimi dhe modifikimi me shumë kthesa.
- Dalje me rezolucion të lartë : Aftësi të integruara gjenerimi për pamje 1K, 2K dhe 4K.
- Imazhja Flash Gemini 3.1 shton rezolucionin më të vogël prej 512px (0.5K).
- Imazhja Gemini 3.1 Flash Lite mbështet vetëm rezolucionin 1K.
- Renderim i avancuar i tekstit : I aftë të gjenerojë tekst të lexueshëm dhe të stilizuar për infografikë, menu, diagrame dhe asete marketingu.
- Bazë me Kërkimin në Google : Modeli mund të përdorë Kërkimin në Google si një mjet për të verifikuar faktet dhe për të gjeneruar imazhe bazuar në të dhëna në kohë reale (p.sh., harta aktuale të motit, grafikë të aksioneve, ngjarje të fundit).
- Nuk mbështetet nga modeli i imazhit Gemini 3.1 Flash Lite.
- Gemini 3.1 Flash Image shton integrimin e Google Image Search Grounding së bashku me Web Search.
- Modaliteti i të menduarit : Modeli përdor një proces "të të menduarit" për të arsyetuar përmes pyetjeve komplekse. Ai gjeneron "imazhe mendimi" të ndërmjetme (të dukshme në sfond, por jo të ngarkuara) për të rafinuar kompozimin përpara se të prodhojë rezultatin përfundimtar me cilësi të lartë.
- Deri në 14 imazhe referuese : Tani mund të përzieni deri në 14 imazhe referuese për të prodhuar imazhin përfundimtar.
- Raporte të reja aspektesh : Gemini 3.1 Flash Lite Image shton raporte aspektesh
1:1,3:2,2:3,3:4,4:3,4:5,5:4,9:16,16:9,21:9.
Përdorni deri në 14 imazhe referuese
Modelet e imazheve Gemini 3 ju lejojnë të përzieni deri në 14 imazhe referuese. Këto 14 imazhe mund të përfshijnë sa vijon:
| Imazh i Gemini 3.1 Flash Lite | Imazh Flash i Gemini 3.1 | Imazh i Gemini 3 Pro |
|---|---|---|
| Deri në 14 imazhe të objekteve me besueshmëri të lartë për t'u përfshirë në imazhin përfundimtar | Deri në 10 imazhe të objekteve me besueshmëri të lartë për t'u përfshirë në imazhin përfundimtar | Deri në 6 imazhe të objekteve me besueshmëri të lartë për t'u përfshirë në imazhin përfundimtar |
| N/A | Deri në 4 imazhe të personazheve për të ruajtur qëndrueshmërinë e personazheve | Deri në 5 imazhe të personazheve për të ruajtur qëndrueshmërinë e personazheve |
| N/A | N/A | Deri në 3 imazhe që mund të përdoren si referenca stili |
Python
from google import genai
from google.genai import types
from PIL import Image
import base64
prompt = "An office group photo of these people, they are making funny faces."
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=[
{
"type": "text",
"text": prompt,
},
{
"type": "image",
"data": base64.b64encode(image_bytes).decode('utf-8'),
"mime_type": "image/png"
},
{
"type": "image",
"data": base64.b64encode(image_bytes).decode('utf-8'),
"mime_type": "image/png"
},
{
"type": "image",
"data": base64.b64encode(image_bytes).decode('utf-8'),
"mime_type": "image/png"
},
{
"type": "image",
"data": base64.b64encode(image_bytes).decode('utf-8'),
"mime_type": "image/png"
},
{
"type": "image",
"data": base64.b64encode(image_bytes).decode('utf-8'),
"mime_type": "image/png"
},
],
response_format={
"type": "image",
"aspect_ratio": "5:4",
"image_size": "2K"
},
)
with open("office.png", "wb") as f:
f.write(base64.b64decode(interaction.output_image.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const input = [
{
type: "text",
text: "An office group photo of these people, they are making funny faces.",
},
{ type: "image", mime_type: "image/jpeg", data: base64ImageFile1 },
{ type: "image", mime_type: "image/jpeg", data: base64ImageFile2 },
{ type: "image", mime_type: "image/jpeg", data: base64ImageFile3 },
{ type: "image", mime_type: "image/jpeg", data: base64ImageFile4 },
{ type: "image", mime_type: "image/jpeg", data: base64ImageFile5 },
];
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: input,
response_format: {
type: "image",
aspect_ratio: "5:4",
image_size: "2K",
},
});
const buffer = Buffer.from(interaction.output_image.data, 'base64');
fs.writeFileSync('office.png', buffer);
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("An office group photo of these people, they are making funny faces."))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d "{
\"model\": \"gemini-3.1-flash-image\",
\"input\": [
{\"type\": \"text\", \"text\": \"An office group photo of these people, they are making funny faces.\"},
{\"type\": \"image\", \"mime_type\": \"image/png\", \"data\": \"<BASE64_DATA_IMG_1>\"},
{\"type\": \"image\", \"mime_type\": \"image/png\", \"data\": \"<BASE64_DATA_IMG_2>\"},
{\"type\": \"image\", \"mime_type\": \"image/png\", \"data\": \"<BASE64_DATA_IMG_3>\"},
{\"type\": \"image\", \"mime_type\": \"image/png\", \"data\": \"<BASE64_DATA_IMG_4>\"},
{\"type\": \"image\", \"mime_type\": \"image/png\", \"data\": \"<BASE64_DATA_IMG_5>\"}
],
\"response_format\": {
\"type\": \"image\",
\"aspect_ratio\": \"5:4\",
\"image_size\": \"2K\"
}
}"
Bazë me Kërkimin në Google
Përdorni mjetin e Kërkimit në Google për të gjeneruar imazhe bazuar në informacione në kohë reale, siç janë parashikimet e motit, grafikët e aksioneve ose ngjarjet e fundit.
Vini re se kur përdorni Grounding me Google Search me gjenerimin e imazheve, rezultatet e kërkimit të bazuara në imazhe nuk i kalohen modelit të gjenerimit dhe përjashtohen nga përgjigja (shih Grounding me Google Image Search )
Python
from google import genai
from google.genai import types
import base64
prompt = "Visualize the current weather forecast for the next 5 days in San Francisco as a clean, modern weather chart. Add a visual on what I should wear each day"
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=prompt,
tools=[{"type": "google_search"}],
response_format={
"type": "image",
"mime_type": "image/jpeg",
"aspect_ratio": "16:9"
},
)
with open("weather.png", "wb") as f:
f.write(base64.b64decode(interaction.output_image.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "Visualize the current weather forecast for the next 5 days in San Francisco as a clean, modern weather chart. Add a visual on what I should wear each day",
tools: [{"type": "google_search"}],
response_format: {
type: "image",
mime_type: "image/png",
aspect_ratio: "16:9",
image_size: "2K"
},
});
const buffer = Buffer.from(interaction.output_image.data, 'base64');
fs.writeFileSync('weather.png', buffer);
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Visualize the current weather forecast for the next 5 days in San Francisco as a clean, modern weather chart. Add a visual on what I should wear each day"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": [
{"type": "text", "text": "Visualize the current weather forecast for the next 5 days in San Francisco as a clean, modern weather chart. Add a visual on what I should wear each day"}
],
"tools": [{"type": "google_search"}],
"response_format": {
"type": "image",
"mime_type": "image/jpeg",
"aspect_ratio": "16:9"
}
}'
Përgjigja përfshin hapat google_search_call dhe google_search_result , së bashku me shënimet e integruara url_citation në hapin e tekstit:
-
google_search_result: Përmbansearch_suggestions, një fragment HTML për paraqitjen e sugjerimeve të kërkimit në ndërfaqen tuaj të përdoruesit. - shënime
url_citation: Citimet e integruara në hapin e tekstit që lidhin pjesë të përgjigjes me burimet e tyre në internet.
Tokëzimi me Kërkimin Google për imazhe (3.1 Flash)
Grounding with Google Image Search u lejon modeleve të përdorin imazhet e uebit të marra nëpërmjet Google Image Search si kontekst vizual për gjenerimin e imazheve. Image Search është një lloj i ri kërkimi brenda mjetit ekzistues Grounding with Google Search, i cili funksionon së bashku me Web Search standard.
Për të aktivizuar Kërkimin e Imazheve, konfiguroni mjetin google_search në kërkesën tuaj API dhe specifikoni image_search brenda vargut search_types . Kërkimi i Imazheve mund të përdoret në mënyrë të pavarur ose së bashku me Kërkimin në Ueb.
Python
from google import genai
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input="A detailed painting of a Timareta butterfly resting on a flower",
tools=[{
"type": "google_search",
"search_types": ["web_search", "image_search"]
}]
)
JavaScript
import { GoogleGenAI } from "@google/genai";
async function main() {
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "A detailed painting of a Timareta butterfly resting on a flower",
tools: [{
"type": "google_search",
"search_types": ["web_search", "image_search"]
}]
});
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("A detailed painting of a Timareta butterfly resting on a flower"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": "A detailed painting of a Timareta butterfly resting on a flower",
"tools": [{"type": "google_search", "search_types": ["web_search", "image_search"]}]
}'
Kërkesat e ekranit
Kur përdorni Kërkimin e Imazheve brenda Grounding me Kërkimin Google, duhet të shfaqni search_suggestions nga hapi google_search_result . Kërkesat e plota të përdorimit janë të detajuara në Kushtet e Shërbimit .
Përgjigje
Për përgjigjet e bazuara duke përdorur kërkimin e imazheve, API kthen citime të brendshme dhe metadata atribuimi si pjesë e hapave të përgjigjes:
shënime
url_citation: Citate të integruara në bllokun e përmbajtjes së tekstit brendamodel_output, duke lidhur përmbajtjen e gjeneruar me burimin e saj.google_search_result: Përmbansearch_suggestions, një fragment HTML për paraqitjen e sugjerimeve të kërkimit në ndërfaqen tuaj të përdoruesit.
Gjenerimi i videos në imazh (3.1 Flash dhe 3.1 Flash Lite)
Gjenerimi i videos në imazh ju lejon të gjeneroni imazhe të reja duke përdorur kontekstin e një videoje si referencë multimodale. Kjo është e dobishme për krijimin e miniaturave të videove me cilësi të lartë, posterave kinematografikë, infografikëve përmbledhës ose veprave të reja artistike të frymëzuara nga një skenë videoje.
Gjatë gjenerimit, modeli analizon kuadrot e videos në kontekst për të nxjerrë temat vizuale dhe ngjarjet kryesore, pastaj i përdor ato së bashku me kërkesën tuaj të tekstit për të sintetizuar imazhin e daljes.
Mund të kaloni URL-të publike të YouTube direkt në kërkesën tuaj të API-t ose të ngarkoni skedarë video lokale duke përdorur API-n e Skedarëve .
Python
from google import genai
from google.genai import types
import base64
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=[
{
"type": "video",
"uri": "https://www.youtube.com/watch?v=UTdfxFyOQTI",
"mime_type": "video/mp4"
},
{"type": "text", "text": "Generate a poster image that captures the key themes of this video."}
],
response_format={"type": "image", "aspect_ratio": "16:9"}
)
# Save the generated image part
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("video_poster.png", "wb") as f:
f.write(base64.b64decode(content_block.data))
print("Image saved as video_poster.png")
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: [
{
type: "video",
uri: "https://www.youtube.com/watch?v=UTdfxFyOQTI",
mime_type: "video/mp4"
},
{ type: "text", text: "Generate a poster image that captures the key themes of this video." }
],
response_format: {
type: "image",
aspect_ratio: "16:9"
}
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("video_poster.png", buffer);
console.log("Image saved as video_poster.png");
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Generate a poster image that captures the key themes of this video."))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "gemini-3.1-flash-image",
"input": [
{
"type": "video",
"uri": "https://www.youtube.com/watch?v=UTdfxFyOQTI",
"mime_type": "video/mp4"
},
{
"type": "text",
"text": "Generate a poster image that captures the key themes of this video."
}
],
"response_format": {
"type": "image",
"aspect_ratio": "16:9"
}
}'
Gjeneroni imazhe me rezolucion deri në 4K
Modelet e imazheve Gemini 3 gjenerojnë imazhe 1K si parazgjedhje, por mund të prodhojnë edhe imazhe 2K, 4K dhe 512px (05.K) (vetëm Imazh Flash Gemini 3.1). Për të gjeneruar asete me rezolucion më të lartë, specifikoni image_size në formatin response_format .
Duhet të përdorni një 'K' me shkronjë të madhe (p.sh. 512px (05.K), 1K, 2K, 4K). Parametrat me shkronjë të vogël (p.sh., 1k) do të refuzohen.
Python
from google import genai
from google.genai import types
import base64
prompt = "Da Vinci style anatomical sketch of a dissected Monarch butterfly. Detailed drawings of the head, wings, and legs on textured parchment with notes in English."
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=prompt,
response_format={
"type": "image",
"mime_type": "image/jpeg",
"aspect_ratio": "1:1",
"image_size": "1K"
},
)
print(interaction.output_text)
with open("butterfly.png", "wb") as f:
f.write(base64.b64decode(interaction.output_image.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "Da Vinci style anatomical sketch of a dissected Monarch butterfly. Detailed drawings of the head, wings, and legs on textured parchment with notes in English.",
response_format: {
type: "image",
mime_type: "image/png",
aspect_ratio: "1:1",
image_size: "1K",
},
});
console.log(interaction.output_text);
const buffer = Buffer.from(interaction.output_image.data, 'base64');
fs.writeFileSync('butterfly.png', buffer);
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Da Vinci style anatomical sketch of a dissected Monarch butterfly. Detailed drawings of the head, wings, and legs on textured parchment with notes in English."))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": "Da Vinci style anatomical sketch of a dissected Monarch butterfly. Detailed drawings of the head, wings, and legs on textured parchment with notes in English.",
"response_format": {
"type": "image",
"mime_type": "image/jpeg",
"aspect_ratio": "1:1",
"image_size": "1K"
}
}'
Më poshtë është një shembull imazhi i gjeneruar nga kjo kërkesë:
Procesi i të menduarit
Modelet e imazheve Gemini 3 janë modele të të menduarit që përdorin një proces arsyetimi ("Thinking") për kërkesa komplekse. Kjo veçori është aktivizuar si parazgjedhje dhe nuk mund të çaktivizohet në API. Për të mësuar më shumë rreth procesit të të menduarit, shihni udhëzuesin Gemini Thinking .
Modeli gjeneron deri në dy imazhe të ndërmjetme për të testuar përbërjen dhe logjikën. Imazhi i fundit brenda Thinking është gjithashtu imazhi përfundimtar i renderuar.
Mund të kontrolloni mendimet që çojnë në imazhin përfundimtar që po prodhohet.
Python
for step in interaction.steps:
if step.type == "thought":
for content_block in step.summary:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
image = Image.open(io.BytesIO(base64.b64decode(content_block.data)))
image.show()
JavaScript
for (const step of interaction.steps) {
if (step.type === "thought") {
for (const contentBlock of step.summary) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, 'base64');
fs.writeFileSync('thought_image.png', buffer);
}
}
}
}
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.8-flash"))
.input(InteractionsInput.of("Image operation"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
Tekst dhe imazhe të ndërthurura
Ndërsa modelet standarde të gjenerimit të imazheve nxjerrin vetëm imazhe, disa modele të përparuara Gemini 3 (siç është gemini-3-pro-image ) mund të gjenerojnë përmbajtje të ndërthurur - si histori ose udhëzues mësimorë që përmbajnë blloqe teksti dhe ilustrime brenda të njëjtës përgjigje.
Meqenëse rezultati është kompleks dhe i ndërthurur, vetitë e përshtatshme si .output_image ose .output_text nuk do ta kapin sekuencën e plotë. Për të aksesuar dhe ruajtur përmbajtjen e ndërthurur, duhet të përsërisni manualisht steps :
Python
interaction = client.interactions.create(
model="gemini-3-pro-image",
input="Write the story of the lifecycle of a monarch butterfly, interleave illustrations",
)
image_counter = 1
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
filename = f"butterfly_lifecycle_{image_counter}.png"
with open(filename, "wb") as f:
f.write(base64.b64decode(content_block.data))
print(f"\n[Saved illustration: {filename}]\n")
image_counter += 1
JavaScript
const interaction = await ai.interactions.create({
model: "gemini-3-pro-image",
input: "Write the story of the lifecycle of a monarch butterfly, interleave illustrations",
});
let imageCounter = 1;
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
const filename = `butterfly_lifecycle_${imageCounter}.png`;
fs.writeFileSync(filename, buffer);
console.log(`\n[Saved illustration: ${filename}]\n`);
imageCounter++;
}
}
}
}
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3-pro-image"))
.input(InteractionsInput.of("Write the story of the lifecycle of a monarch butterfly, interleave illustrations"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
Kontrollimi i niveleve të të menduarit
Me Gemini 3.1 Flash Image dhe Gemini 3.1 Flash Lite Image, mund të kontrolloni sasinë e të menduarit që përdor modeli për të balancuar cilësinë dhe vonesën. Niveli i parazgjedhur thinking_level është minimal , dhe nivelet e mbështetura janë minimal dhe high .
Python
from google import genai
from PIL import Image
import base64
import io
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input="A futuristic city built inside a giant glass bottle floating in space",
generation_config={"thinking_level": "high"},
)
print(interaction.output_text)
image = Image.open(io.BytesIO(base64.b64decode(interaction.output_image.data)))
image.show()
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "A futuristic city built inside a giant glass bottle floating in space",
generation_config: { thinking_level: "high" },
});
console.log(interaction.output_text);
const buffer = Buffer.from(interaction.output_image.data, 'base64');
fs.writeFileSync('image.png', buffer);
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("A futuristic city built inside a giant glass bottle floating in space"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": "A futuristic city built inside a giant glass bottle floating in space",
"generation_config": {
"thinking_level": "high"
}
}'
Vini re se tokenët e të menduarit faturohen si parazgjedhje për modelet e të menduarit, pasi procesi i të menduarit ndodh gjithmonë si parazgjedhje, pavarësisht nëse e shikoni procesin apo jo.
Mënyra të tjera të gjenerimit të imazheve
Edhe pse modelet e gjenerimit të imazheve Nano Banana rekomandohen për shumicën e rasteve të përdorimit, mund të eksploroni edhe modele të dedikuara të gjenerimit të imazheve:
- Imazh : Modelet e konvertimit tekst-në-imazh të Google-it të optimizuara për gjenerimin e imazheve me cilësi të lartë.
- Veo : Modeli i gjenerimit të videove i Google-it.
Gjeneroni imazhe në grup
Të gjitha aftësitë e gjenerimit të imazheve të përshkruara në këtë faqe mund të ekzekutohen edhe si punë në grup duke përdorur Batch API , i cili është ideal nëse duhet të gjeneroni shumë imazhe. Ju merrni kufij më të lartë shpejtësie në këmbim të një kthese deri në 24 orë.
Udhëzues dhe strategji nxitëse
Ky seksion ofron shembuj dhe shabllone për rrjedhat e zakonshme të punës për gjenerimin dhe redaktimin e imazheve. Çdo shembull përfshin një shabllon të ripërdorshëm dhe një shembull për API-në e Ndërveprimeve.
Udhëzime për gjenerimin e imazheve
Shembujt e mëposhtëm tregojnë se si të përdoren udhëzimet me tekst për të gjeneruar lloje të ndryshme imazhesh.
1. Skena fotorealiste
Përshkruani një skenë me shumë detaje. Sa më specifik të jeni, aq më shumë kontroll keni mbi rezultatet.
Shabllon
A photorealistic [type of shot] of a [subject description] in a [setting
description]. [Description of the light]. Shot from a [camera angle]
with a [lens type].
Nxitje
A photorealistic wide-angle shot of a vibrant coral reef teeming with tropical fish. Crystal-clear turquoise water with sunbeams filtering down from the surface, illuminating a sea turtle gliding gracefully over the coral. Shot from a low perspective with a wide-angle lens. Aspect ratio 16:9.
Python
from google import genai
from google.genai import types
import base64
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input="A photorealistic wide-angle shot of a vibrant coral reef teeming with tropical fish. Crystal-clear turquoise water with sunbeams filtering down from the surface, illuminating a sea turtle gliding gracefully over the coral. Shot from a low perspective with a wide-angle lens. Aspect ratio 16:9.",
response_format=[
{
"type": "image",
"mime_type": "image/jpeg",
"aspect_ratio": "16:9",
}
],
)
print(interaction.output_text)
with open("coral_reef.png", "wb") as f:
f.write(base64.b64decode(interaction.output_image.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "A photorealistic wide-angle shot of a vibrant coral reef teeming with tropical fish. Crystal-clear turquoise water with sunbeams filtering down from the surface, illuminating a sea turtle gliding gracefully over the coral. Shot from a low perspective with a wide-angle lens. Aspect ratio 16:9.",
response_format: [
{
type: "image",
mime_type: "image/jpeg",
aspect_ratio: "16:9",
}
],
});
console.log(interaction.output_text);
const buffer = Buffer.from(interaction.output_image.data, 'base64');
fs.writeFileSync('coral_reef.png', buffer);
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("A photorealistic wide-angle shot of a vibrant coral reef teeming with tropical fish. Crystal-clear turquoise water with sunbeams filtering down from the surface, illuminating a sea turtle gliding gracefully over the coral. Shot from a low perspective with a wide-angle lens. Aspect ratio 16:9."))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": "A photorealistic wide-angle shot of a vibrant coral reef teeming with tropical fish. Crystal-clear turquoise water with sunbeams filtering down from the surface, illuminating a sea turtle gliding gracefully over the coral. Shot from a low perspective with a wide-angle lens. Aspect ratio 16:9.",
"response_format": {
"type": "image",
"mime_type": "image/png",
"aspect_ratio": "16:9"
}
}'
2. Ilustrime dhe afishe të stilizuara
Përshkruani stilin artistik, subjektin dhe mediumin. Jini specifik në lidhje me detajet vizuale (linjat e theksuara, ngjyrat, etj.) për rezultate të qëndrueshme.
Shabllon
A [style] of a [subject, with details about accessories or actions]
doing [activity]. The design features [visual qualities, e.g., bold outlines,
cel-shading, etc.] and [color/background preference].
Nxitje
A kawaii-style sticker of a happy red panda wearing a tiny bamboo hat. It's munching on a green bamboo leaf. The design features bold, clean outlines, simple cel-shading, and a vibrant color palette. The background must be white.
Python
from google import genai
import base64
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input="A kawaii-style sticker of a happy red panda wearing a tiny bamboo hat. It's munching on a green bamboo leaf. The design features bold, clean outlines, simple cel-shading, and a vibrant color palette. The background must be white.",
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("red_panda_sticker.png", "wb") as f:
f.write(base64.b64decode(content_block.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "A kawaii-style sticker of a happy red panda wearing a tiny bamboo hat. It's munching on a green bamboo leaf. The design features bold, clean outlines, simple cel-shading, and a vibrant color palette. The background must be white.",
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("red_panda_sticker.png", buffer);
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("A kawaii-style sticker of a happy red panda wearing a tiny bamboo hat. It"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": "A kawaii-style sticker of a happy red panda wearing a tiny bamboo hat. It is munching on a green bamboo leaf. The design features bold, clean outlines, simple cel-shading, and a vibrant color palette. The background must be white."
}'
3. Tekst i saktë në imazhe
Gemini shkëlqen në paraqitjen e tekstit. Jini të qartë në lidhje me tekstin, stilin e shkronjave (në mënyrë përshkruese) dhe dizajnin e përgjithshëm. Përdorni Gemini 3 Pro Image për prodhim profesional të aseteve.
Shabllon
Create a [image type] for [brand/concept] with the text "[text to render]"
in a [font style]. The design should be [style description], with a
[color scheme].
Nxitje
Create a modern, minimalist logo for a coffee shop called 'The Daily Grind'. The text should be in a clean, bold, sans-serif font. The color scheme is black and white. Put the logo in a circle. Use a coffee bean in a clever way.
Python
from google import genai
import base64
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input="Create a modern, minimalist logo for a coffee shop called 'The Daily Grind'. The text should be in a clean, bold, sans-serif font. The color scheme is black and white. Put the logo in a circle. Use a coffee bean in a clever way.",
response_format={"type": "image", "aspect_ratio": "1:1"},
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("logo_example.jpg", "wb") as f:
f.write(base64.b64decode(content_block.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "Create a modern, minimalist logo for a coffee shop called 'The Daily Grind'. The text should be in a clean, bold, sans-serif font. The color scheme is black and white. Put the logo in a circle. Use a coffee bean in a clever way.",
response_format: { type: "image", aspect_ratio: "1:1" },
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("logo_example.jpg", buffer);
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Create a modern, minimalist logo for a coffee shop called "))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": "Create a modern, minimalist logo for a coffee shop called The Daily Grind. The text should be in a clean, bold, sans-serif font. The color scheme is black and white. Put the logo in a circle. Use a coffee bean in a clever way.",
"response_format": {
"type": "image",
"aspect_ratio": "1:1"
}
}'
4. Makete produktesh dhe fotografi komerciale
Perfekt për krijimin e fotove të pastra dhe profesionale të produkteve për tregtinë elektronike, reklamimin ose krijimin e markave.
Shabllon
A high-resolution, studio-lit product photograph of a [product description]
on a [background surface/description]. The lighting is a [lighting setup,
e.g., three-point softbox setup] to [lighting purpose]. The camera angle is
a [angle type] to showcase [specific feature]. Ultra-realistic, with sharp
focus on [key detail]. [Aspect ratio].
Nxitje
A high-resolution, studio-lit product photograph of a minimalist ceramic
coffee mug in matte black, presented on a polished concrete surface. The
lighting is a three-point softbox setup designed to create soft, diffused
highlights and eliminate harsh shadows. The camera angle is a slightly
elevated 45-degree shot to showcase its clean lines. Ultra-realistic, with
sharp focus on the steam rising from the coffee. Square image.
Python
from google import genai
import base64
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input="A high-resolution, studio-lit product photograph of a minimalist ceramic coffee mug in matte black, presented on a polished concrete surface. The lighting is a three-point softbox setup designed to create soft, diffused highlights and eliminate harsh shadows. The camera angle is a slightly elevated 45-degree shot to showcase its clean lines. Ultra-realistic, with sharp focus on the steam rising from the coffee. Square image.",
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("product_mockup.png", "wb") as f:
f.write(base64.b64decode(content_block.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "A high-resolution, studio-lit product photograph of a minimalist ceramic coffee mug in matte black, presented on a polished concrete surface. The lighting is a three-point softbox setup designed to create soft, diffused highlights and eliminate harsh shadows. The camera angle is a slightly elevated 45-degree shot to showcase its clean lines. Ultra-realistic, with sharp focus on the steam rising from the coffee. Square image.",
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("product_mockup.png", buffer);
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("A high-resolution, studio-lit product photograph of a minimalist ceramic coffee mug in matte black, presented on a polished concrete surface. The lighting is a three-point softbox setup designed to create soft, diffused highlights and eliminate harsh shadows. The camera angle is a slightly elevated 45-degree shot to showcase its clean lines. Ultra-realistic, with sharp focus on the steam rising from the coffee. Square image."))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": "A high-resolution, studio-lit product photograph of a minimalist ceramic coffee mug in matte black, presented on a polished concrete surface. The lighting is a three-point softbox setup designed to create soft, diffused highlights and eliminate harsh shadows. The camera angle is a slightly elevated 45-degree shot to showcase its clean lines. Ultra-realistic, with sharp focus on the steam rising from the coffee. Square image."
}'
5. Dizajn minimalist dhe negativ i hapësirës
Shkëlqyeshëm për krijimin e sfondeve për faqet e internetit, prezantimet ose materialet e marketingut ku teksti do të mbivendoset.
Shabllon
A minimalist composition featuring a single [subject] positioned in the
[bottom-right/top-left/etc.] of the frame. The background is a vast, empty
[color] canvas, creating significant negative space. Soft, subtle lighting.
[Aspect ratio].
Nxitje
A minimalist composition featuring a single, delicate red maple leaf
positioned in the bottom-right of the frame. The background is a vast, empty
off-white canvas, creating significant negative space for text. Soft,
diffused lighting from the top left. Square image.
Python
from google import genai
import base64
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input="A minimalist composition featuring a single, delicate red maple leaf positioned in the bottom-right of the frame. The background is a vast, empty off-white canvas, creating significant negative space for text. Soft, diffused lighting from the top left. Square image.",
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("minimalist_design.png", "wb") as f:
f.write(base64.b64decode(content_block.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "A minimalist composition featuring a single, delicate red maple leaf positioned in the bottom-right of the frame. The background is a vast, empty off-white canvas, creating significant negative space for text. Soft, diffused lighting from the top left. Square image.",
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("minimalist_design.png", buffer);
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("A minimalist composition featuring a single, delicate red maple leaf positioned in the bottom-right of the frame. The background is a vast, empty off-white canvas, creating significant negative space for text. Soft, diffused lighting from the top left. Square image."))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": "A minimalist composition featuring a single, delicate red maple leaf positioned in the bottom-right of the frame. The background is a vast, empty off-white canvas, creating significant negative space for text. Soft, diffused lighting from the top left. Square image."
}'
6. Art sekuencial (panel komik / storyboard)
Ndërtohet mbi qëndrueshmërinë e personazheve dhe përshkrimin e skenës për të krijuar panele për rrëfim vizual. Për saktësi me tekstin dhe aftësinë e rrëfimit, këto sugjerime funksionojnë më mirë me Gemini 3 Pro dhe Gemini 3.1 Flash Image.
Shabllon
Make a 3 panel comic in a [style]. Put the character in a [type of scene].
Nxitje
Make a 3 panel comic in a gritty, noir art style with high-contrast black and white inks. Put the character in a humurous scene.
Python
from google import genai
from PIL import Image
import base64
client = genai.Client()
with open('/path/to/your/man_in_white_glasses.jpg', 'rb') as f:
image_bytes = f.read()
text_input = "Make a 3 panel comic in a gritty, noir art style with high-contrast black and white inks. Put the character in a humurous scene."
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=[
{"type": "text", "text": text_input},
{
"type": "image",
"data": base64.b64encode(image_bytes).decode('utf-8'),
"mime_type": "image/jpeg"
}
],
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("comic_panel.jpg", "wb") as f:
f.write(base64.b64decode(content_block.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const imagePath = "/path/to/your/man_in_white_glasses.jpg";
const imageData = fs.readFileSync(imagePath);
const base64Image = imageData.toString("base64");
const input = [
{ type: "text", text: "Make a 3 panel comic in a gritty, noir art style with high-contrast black and white inks. Put the character in a humurous scene." },
{
type: "image",
mime_type: "image/jpeg",
data: base64Image
},
];
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: input,
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("comic_panel.jpg", buffer);
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Make a 3 panel comic in a gritty, noir art style with high-contrast black and white inks. Put the character in a humurous scene."))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": [
{"type": "text", "text": "Make a 3 panel comic in a gritty, noir art style with high-contrast black and white inks. Put the character in a humurous scene."},
{"type": "image", "data": "<BASE64_IMAGE_DATA>", "mime_type": "image/jpeg"}
]
}'
Hyrje | Prodhimi |
 |  |
7. Bazë me Kërkimin në Google
Përdorni Kërkimin në Google për të gjeneruar imazhe bazuar në informacione të fundit ose në kohë reale. Kjo është e dobishme për lajmet, motin dhe tema të tjera të ndjeshme ndaj kohës.
Nxitje
Make a simple but stylish graphic of last night's Arsenal game in the Champion's League
Python
from google import genai
from google.genai import types
import base64
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input="Make a simple but stylish graphic of last night's Arsenal game in the Champion's League",
tools=[{"type": "google_search"}],
response_format={"type": "image", "aspect_ratio": "16:9"},
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("football-score.jpg", "wb") as f:
f.write(base64.b64decode(content_block.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "Make a simple but stylish graphic of last night's Arsenal game in the Champion's League",
tools: [{ type: "google_search" }],
response_format: { type: "image", aspect_ratio: "16:9", image_size: "2K" },
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("football-score.jpg", buffer);
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Make a simple but stylish graphic of last night"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": "Make a simple but stylish graphic of last nights Arsenal game in the Champions League",
"tools": [{"type": "google_search"}],
"response_format": {
"type": "image",
"aspect_ratio": "16:9"
}
}'
Udhëzime për redaktimin e imazheve
Këto shembuj tregojnë se si të ofroni imazhe së bashku me kërkesat e tekstit për redaktim, kompozim dhe transferim stili.
1. Shtimi dhe heqja e elementeve
Jepni një imazh dhe përshkruani ndryshimin tuaj. Modeli do të përputhet me stilin, ndriçimin dhe perspektivën e imazhit origjinal.
Shabllon
Using the provided image of [subject], please [add/remove/modify] [element]
to/from the scene. Ensure the change is [description of how the change should
integrate].
Nxitje
"Using the provided image of my cat, please add a small, knitted wizard hat
on its head. Make it look like it's sitting comfortably and matches the soft
lighting of the photo."
Python
from google import genai
from PIL import Image
import base64
client = genai.Client()
with open('/path/to/your/cat_photo.png', 'rb') as f:
image_bytes = f.read()
text_input = """Using the provided image of my cat, please add a small, knitted wizard hat on its head. Make it look like it's sitting comfortably and not falling off."""
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=[
{"type": "text", "text": text_input},
{
"type": "image",
"data": base64.b64encode(image_bytes).decode('utf-8'),
"mime_type": "image/png"
}
],
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("cat_with_hat.png", "wb") as f:
f.write(base64.b64decode(content_block.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const imagePath = "/path/to/your/cat_photo.png";
const imageData = fs.readFileSync(imagePath);
const base64Image = imageData.toString("base64");
const input = [
{ type: "text", text: "Using the provided image of my cat, please add a small, knitted wizard hat on its head. Make it look like it's sitting comfortably and not falling off." },
{
type: "image",
mime_type: "image/png",
data: base64Image
},
];
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: input,
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("cat_with_hat.png", buffer);
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Using the provided image of my cat, please add a small, knitted wizard hat on its head. Make it look like it"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d "{
\"model\": \"gemini-3.1-flash-image\",
\"input\": [
{\"type\": \"text\", \"text\": \"Using the provided image of my cat, please add a small, knitted wizard hat on its head. Make it look like it's sitting comfortably and not falling off.\"},
{\"type\": \"image\", \"mime_type\":\"image/png\", \"data\": \"<BASE64_IMAGE_DATA>\"}
]
}"
Hyrje | Prodhimi |
 |  |
2. Inpainting (maskim semantik)
Përcaktoni në mënyrë bisedore një "maskë" për të modifikuar një pjesë specifike të një imazhi duke e lënë pjesën tjetër të paprekur.
Shabllon
Using the provided image, change only the [specific element] to [new
element/description]. Keep everything else in the image exactly the same,
preserving the original style, lighting, and composition.
Nxitje
"Using the provided image of a living room, change only the blue sofa to be
a vintage, brown leather chesterfield sofa. Keep the rest of the room,
including the pillows on the sofa and the lighting, unchanged."
Python
from google import genai
from PIL import Image
import base64
client = genai.Client()
with open('/path/to/your/living_room.png', 'rb') as f:
image_bytes = f.read()
text_input = """Using the provided image of a living room, change only the blue sofa to be a vintage, brown leather chesterfield sofa. Keep the rest of the room, including the pillows on the sofa and the lighting, unchanged."""
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=[
{
"type": "image",
"data": base64.b64encode(image_bytes).decode('utf-8'),
"mime_type": "image/png"
},
{"type": "text", "text": text_input}
],
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("living_room_edited.png", "wb") as f:
f.write(base64.b64decode(content_block.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const imagePath = "/path/to/your/living_room.png";
const imageData = fs.readFileSync(imagePath);
const base64Image = imageData.toString("base64");
const input = [
{
type: "image",
mime_type: "image/png",
data: base64Image
},
{ type: "text", text: "Using the provided image of a living room, change only the blue sofa to be a vintage, brown leather chesterfield sofa. Keep the rest of the room, including the pillows on the sofa and the lighting, unchanged." },
];
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: input,
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("living_room_edited.png", buffer);
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Using the provided image of a living room, change only the blue sofa to be a vintage, brown leather chesterfield sofa. Keep the rest of the room, including the pillows on the sofa and the lighting, unchanged."))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d "{
\"model\": \"gemini-3.1-flash-image\",
\"input\": [
{\"type\": \"image\", \"mime_type\":\"image/png\", \"data\": \"<BASE64_IMAGE_DATA>\"},
{\"type\": \"text\", \"text\": \"Using the provided image of a living room, change only the blue sofa to be a vintage, brown leather chesterfield sofa. Keep the rest of the room, including the pillows on the sofa and the lighting, unchanged.\"}
]
}"
Hyrje | Prodhimi |
 |  |
3. Transferimi i stilit
Jepni një imazh dhe kërkojini modelit të rikrijojë përmbajtjen e tij në një stil artistik të ndryshëm.
Shabllon
Transform the provided photograph of [subject] into the artistic style of [artist/art style]. Preserve the original composition but render it with [description of stylistic elements].
Nxitje
"Transform the provided photograph of a modern city street at night into the artistic style of Vincent van Gogh's 'Starry Night'. Preserve the original composition of buildings and cars, but render all elements with swirling, impasto brushstrokes and a dramatic palette of deep blues and bright yellows."
Python
from google import genai
from PIL import Image
import base64
client = genai.Client()
with open('/path/to/your/city.png', 'rb') as f:
image_bytes = f.read()
text_input = """Transform the provided photograph of a modern city street at night into the artistic style of Vincent van Gogh's 'Starry Night'. Preserve the original composition of buildings and cars, but render all elements with swirling, impasto brushstrokes and a dramatic palette of deep blues and bright yellows."""
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=[
{
"type": "image",
"data": base64.b64encode(image_bytes).decode('utf-8'),
"mime_type": "image/png"
},
{"type": "text", "text": text_input}
],
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("city_style_transfer.png", "wb") as f:
f.write(base64.b64decode(content_block.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const imageData = fs.readFileSync("/path/to/your/city.png");
const base64Image = imageData.toString("base64");
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: [
{
type: "image",
mime_type: "image/png",
data: base64Image
},
{ type: "text", text: "Transform the provided photograph of a modern city street at night into the artistic style of Vincent van Gogh's 'Starry Night'. Preserve the original composition of buildings and cars, but render all elements with swirling, impasto brushstrokes and a dramatic palette of deep blues and bright yellows." },
],
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("city_style_transfer.png", buffer);
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Transform the provided photograph of a modern city street at night into the artistic style of Vincent van Gogh"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d "{
\"model\": \"gemini-3.1-flash-image\",
\"input\": [
{\"type\": \"image\", \"mime_type\":\"image/png\", \"data\": \"<BASE64_IMAGE_DATA>\"},
{\"type\": \"text\", \"text\": \"Transform the provided photograph of a modern city street at night into the artistic style of Vincent van Gogh's 'Starry Night'. Preserve the original composition of buildings and cars, but render all elements with swirling, impasto brushstrokes and a dramatic palette of deep blues and bright yellows.\"}
]
}"
Hyrje | Prodhimi |
 |  |
4. Kompozim i avancuar: kombinimi i imazheve të shumëfishta
Jepni imazhe të shumta si kontekst për të krijuar një skenë të re, të përbërë. Kjo është perfekte për makete produktesh ose kolazhe krijuese.
Shabllon
Create a new image by combining the elements from the provided images. Take
the [element from image 1] and place it with/on the [element from image 2].
The final image should be a [description of the final scene].
Nxitje
"Create a professional e-commerce fashion photo. Take the blue floral dress
from the first image and let the woman from the second image wear it.
Generate a realistic, full-body shot of the woman wearing the dress, with
the lighting and shadows adjusted to match the outdoor environment."
Python
from google import genai
from PIL import Image
import base64
client = genai.Client()
with open('/path/to/your/dress.png', 'rb') as f:
dress_bytes = f.read()
with open('/path/to/your/model.png', 'rb') as f:
model_bytes = f.read()
text_input = """Create a professional e-commerce fashion photo. Take the blue floral dress from the first image and let the woman from the second image wear it. Generate a realistic, full-body shot of the woman wearing the dress, with the lighting and shadows adjusted to match the outdoor environment."""
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=[
{
"type": "image",
"data": base64.b64encode(dress_bytes).decode('utf-8'),
"mime_type": "image/png"
},
{
"type": "image",
"data": base64.b64encode(model_bytes).decode('utf-8'),
"mime_type": "image/png"
},
{"type": "text", "text": text_input}
],
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("fashion_ecommerce_shot.png", "wb") as f:
f.write(base64.b64decode(content_block.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const imagePath1 = "/path/to/your/dress.png";
const imageData1 = fs.readFileSync(imagePath1);
const base64Image1 = imageData1.toString("base64");
const imagePath2 = "/path/to/your/model.png";
const imageData2 = fs.readFileSync(imagePath2);
const base64Image2 = imageData2.toString("base64");
const input = [
{
type: "image",
mime_type: "image/png",
data: base64Image1
},
{
type: "image",
mime_type: "image/png",
data: base64Image2
},
{ type: "text", text: "Create a professional e-commerce fashion photo. Take the blue floral dress from the first image and let the woman from the second image wear it. Generate a realistic, full-body shot of the woman wearing the dress, with the lighting and shadows adjusted to match the outdoor environment." },
];
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: input,
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("fashion_ecommerce_shot.png", buffer);
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Create a professional e-commerce fashion photo. Take the blue floral dress from the first image and let the woman from the second image wear it. Generate a realistic, full-body shot of the woman wearing the dress, with the lighting and shadows adjusted to match the outdoor environment."))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d "{
\"model\": \"gemini-3.1-flash-image\",
\"input\": [
{\"type\": \"image\", \"mime_type\":\"image/png\", \"data\": \"<BASE64_IMAGE_DATA_1>\"},
{\"type\": \"image\", \"mime_type\":\"image/png\", \"data\": \"<BASE64_IMAGE_DATA_2>\"},
{\"type\": \"text\", \"text\": \"Create a professional e-commerce fashion photo. Take the blue floral dress from the first image and let the woman from the second image wear it. Generate a realistic, full-body shot of the woman wearing the dress, with the lighting and shadows adjusted to match the outdoor environment.\"}
}]
}"
Hyrja 1 | Hyrja 2 | Prodhimi |
 |  |  |
5. Ruajtja e detajeve me besnikëri të lartë
Për t'u siguruar që detajet kritike (si një fytyrë ose logo) ruhen gjatë një redaktimi, përshkruajini ato me shumë detaje së bashku me kërkesën tuaj për redaktim.
Shabllon
Using the provided images, place [element from image 2] onto [element from
image 1]. Ensure that the features of [element from image 1] remain
completely unchanged. The added element should [description of how the
element should integrate].
Nxitje
"Take the first image of the woman with brown hair, blue eyes, and a neutral
expression. Add the logo from the second image onto her black t-shirt.
Ensure the woman's face and features remain completely unchanged. The logo
should look like it's naturally printed on the fabric, following the folds
of the shirt."
Python
from google import genai
from PIL import Image
import base64
client = genai.Client()
with open('/path/to/your/woman.png', 'rb') as f:
woman_bytes = f.read()
with open('/path/to/your/logo.png', 'rb') as f:
logo_bytes = f.read()
text_input = """Take the first image of the woman with brown hair, blue eyes, and a neutral expression. Add the logo from the second image onto her black t-shirt. Ensure the woman's face and features remain completely unchanged. The logo should look like it's naturally printed on the fabric, following the folds of the shirt."""
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=[
{"type": "image", "mime_type":"image/png", "data": base64.b64encode(woman_bytes).decode('utf-8')},
{"type": "image", "mime_type":"image/png", "data": base64.b64encode(logo_bytes).decode('utf-8')},
{"type": "text", "text": text_input}
],
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("woman_with_logo.png", "wb") as f:
f.write(base64.b64decode(content_block.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const imagePath1 = "/path/to/your/woman.png";
const imageData1 = fs.readFileSync(imagePath1);
const base64Image1 = imageData1.toString("base64");
const imagePath2 = "/path/to/your/logo.png";
const imageData2 = fs.readFileSync(imagePath2);
const base64Image2 = imageData2.toString("base64");
const input = [
{"type": "image", "mime_type":"image/png", "data": base64Image1},
{"type": "image", "mime_type":"image/png", "data": base64Image2},
{"type": "text", "text": "Take the first image of the woman with brown hair, blue eyes, and a neutral expression. Add the logo from the second image onto her black t-shirt. Ensure the woman's face and features remain completely unchanged. The logo should look like it's naturally printed on the fabric, following the folds of the shirt."},
];
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: input,
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("woman_with_logo.png", buffer);
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("model_output"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d "{
\"model\": \"gemini-3.1-flash-image\",
\"input\": [
{\"type\": \"image\", \"mime_type\":\"image/png\", \"data\": \"<BASE64_IMAGE_DATA_1>\"},
{\"type\": \"image\", \"mime_type\":\"image/png\", \"data\": \"<BASE64_IMAGE_DATA_2>\"},
{\"type\": \"text\", \"text\": \"Take the first image of the woman with brown hair, blue eyes, and a neutral expression. Add the logo from the second image onto her black t-shirt. Ensure the woman's face and features remain completely unchanged. The logo should look like it's naturally printed on the fabric, following the folds of the shirt.\"}
]
}"
Hyrja 1 | Hyrja 2 | Prodhimi |
 |  |  |
6. Jepini jetë diçkaje
Ngarko një skicë ose vizatim të përafërt dhe kërkoji modelit ta rafinojë atë në një imazh të përfunduar.
Shabllon
Turn this rough [medium] sketch of a [subject] into a [style description]
photo. Keep the [specific features] from the sketch but add [new details/materials].
Nxitje
"Turn this rough pencil sketch of a futuristic car into a polished photo of the finished concept car in a showroom. Keep the sleek lines and low profile from the sketch but add metallic blue paint and neon rim lighting."
Python
from google import genai
from PIL import Image
import base64
client = genai.Client()
with open('/path/to/your/car_sketch.png', 'rb') as f:
sketch_bytes = f.read()
text_input = """Turn this rough pencil sketch of a futuristic car into a polished photo of the finished concept car in a showroom. Keep the sleek lines and low profile from the sketch but add metallic blue paint and neon rim lighting."""
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=[
{"type": "image", "mime_type":"image/png", "data": base64.b64encode(sketch_bytes).decode('utf-8')},
{"type": "text", "text": text_input}
],
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("car_photo.png", "wb") as f:
f.write(base64.b64decode(content_block.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const imagePath = "/path/to/your/car_sketch.png";
const imageData = fs.readFileSync(imagePath);
const base64Image = imageData.toString("base64");
const input = [
{"type": "image", "mime_type":"image/png", "data": base64Image},
{"type": "text", "text": "Turn this rough pencil sketch of a futuristic car into a polished photo of the finished concept car in a showroom. Keep the sleek lines and low profile from the sketch but add metallic blue paint and neon rim lighting."},
];
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: input,
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("car_photo.png", buffer);
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("model_output"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d "{
\"model\": \"gemini-3.1-flash-image\",
\"input\": [
{\"type\": \"image\", \"mime_type\":\"image/png\", \"data\": \"<BASE64_IMAGE_DATA>\"},
{\"type\": \"text\", \"text\": \"Turn this rough pencil sketch of a futuristic car into a polished photo of the finished concept car in a showroom. Keep the sleek lines and low profile from the sketch but add metallic blue paint and neon rim lighting.\"}
]
}"
Hyrje | Prodhimi |
 |  |
7. Konsistenca e personazheve: Pamje 360 gradë
Mund të gjeneroni pamje 360 gradë të një personazhi duke kërkuar në mënyrë iterative kënde të ndryshme. Për rezultate më të mira, përfshini imazhe të gjeneruara më parë në kërkesat pasuese për të ruajtur qëndrueshmërinë. Për poza komplekse, përfshini një imazh reference të pozës së zgjedhur.
Shabllon
A studio portrait of [person] against [background], [looking forward/in profile looking right/etc.]
Nxitje
A studio portrait of this man against white, in profile looking right
Python
from google import genai
from PIL import Image
import base64
client = genai.Client()
with open('/path/to/your/man_in_white_glasses.jpg', 'rb') as f:
image_bytes = f.read()
text_input = """A studio portrait of this man against white, in profile looking right"""
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input={
{"type": "text", "text": text_input},
{"type": "image", "mime_type":"image/png", "data": base64.b64encode(image_bytes).decode('utf-8')}
},
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("man_right_profile.png", "wb") as f:
f.write(base64.b64decode(content_block.data))
Hyrje | Dalja 1 | Dalja 2 |
|  |  |
Praktikat më të mira
Për t'i përmirësuar rezultatet tuaja nga të mira në të shkëlqyera, përfshini këto strategji profesionale në rrjedhën tuaj të punës.
- Ji hiper-specifik: Sa më shumë detaje të japësh, aq më shumë kontroll ke. Në vend të "armaturës fantazi", përshkruaje atë: "armaturë e zbukuruar me pllaka elfësh, e gdhendur me modele gjethesh argjendi, me një jakë të lartë dhe pauldronë në formën e krahëve të skifterit".
- Jepni kontekstin dhe qëllimin: Shpjegoni qëllimin e imazhit. Kuptimi i kontekstit nga modeli do të ndikojë në rezultatin përfundimtar. Për shembull, "Krijo një logo për një markë të nivelit të lartë dhe minimaliste për kujdesin e lëkurës" do të japë rezultate më të mira sesa thjesht "Krijo një logo".
- Përsërite dhe përsos: Mos prit një imazh perfekt që në provën e parë. Përdor natyrën bisedore të modelit për të bërë ndryshime të vogla. Ndiq pyetje të tilla si: "Kjo është shumë mirë, por a mund ta bësh ndriçimin pak më të ngrohtë?" ose "Mbaje gjithçka të njëjtë, por ndrysho shprehjen e personazhit që të jetë më serioze".
- Përdorni udhëzime hap pas hapi: Për skena komplekse me shumë elementë, ndajeni kërkesën tuaj në hapa. "Së pari, krijoni një sfond të një pylli të qetë dhe me mjegull në agim. Pastaj, në plan të parë, shtoni një altar të lashtë prej guri të mbuluar me myshk. Së fundmi, vendosni një shpatë të vetme që ndriçon sipër altarit."
- Përdorni "nxitje semantike negative": Në vend që të thoni "pa makina", përshkruajeni skenën e synuar pozitivisht: "një rrugë e zbrazët, e shkretë pa shenja trafiku".
- Kontrolloni kamerën: Përdorni gjuhë fotografike dhe kinematografike për të kontrolluar kompozimin. Terma si
wide-angle shot,macro shot,low-angle perspective.
Kufizime
- Për performancën më të mirë, përdorni gjuhët e mëposhtme: EN, ar-EG, de-DE, es-MX, fr-FR, hi-IN, id-ID, it-IT, ja-JP, ko-KR, pt-BR, ru-RU, ua-UA, vi-VN, zh-CN.
- Gjenerimi i imazheve nuk mbështet hyrjet audio. Hyrjet video mbështeten vetëm për Gemini 3.1 Flash Image dhe Gemini 3.1 Flash Lite Image.
- Modeli nuk do të ndjekë gjithmonë numrin e saktë të rezultateve të imazheve që përdoruesi kërkon në mënyrë të qartë.
-
gemini-2.5-flash-imagefunksionon më së miri me deri në 3 imazhe si të dhëna hyrëse, ndërsagemini-3-pro-imagembështet 5 imazhe me besueshmëri të lartë dhe deri në 14 imazhe në total.gemini-3.1-flash-imagembështet ngjashmërinë e personazheve deri në 4 personazhe dhe besnikërinë e deri në 10 objekteve në një rrjedhë të vetme pune. - Kur gjeneroni tekst për një imazh, Gemini funksionon më mirë nëse së pari gjeneroni tekstin dhe më pas kërkoni një imazh me tekstin.
-
gemini-3.1-flash-imageBazimi me Kërkimin Google nuk mbështet përdorimin e imazheve të botës reale të njerëzve nga kërkimi në internet për momentin. - Të gjitha imazhet e gjeneruara përfshijnë një filigran SynthID .
Konfigurime opsionale
Mund të konfiguroni opsionalisht formatin e daljes, raportin e aspektit dhe madhësinë e imazhit duke përdorur parametrin response_format .
Formati i daljes
Modeli, si parazgjedhje, kthen përgjigje si me tekst, ashtu edhe me imazh. Mund ta konfiguroni përgjigjen për të kthyer vetëm imazhet e gjeneruara (duke hequr tekstin e bisedës) duke specifikuar një format imazhi në parametrin response_format .
Për të kërkuar modalitete të shumëfishta (për shembull, si tekstin ashtu edhe imazhin e gjeneruar), kaloni një varg hyrjesh formati te response_format .
Python
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input="Write a short poem about a starry night and generate an image of it.",
response_format=[
{"type": "text"},
{"type": "image"},
],
)
JavaScript
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "Write a short poem about a starry night and generate an image of it.",
response_format: [
{ type: "text" },
{ type: "image" },
],
});
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Write a short poem about a starry night and generate an image of it."))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "gemini-3.1-flash-image",
"input": "Write a short poem about a starry night and generate an image of it.",
"response_format": [
{ "type": "text" },
{ "type": "image" }
]
}'
Raportet e aspektit dhe madhësia e imazhit
Si parazgjedhje, modeli përputh madhësinë e imazhit të daljes me atë të imazhit tuaj hyrës, ose përndryshe gjeneron katrorë 1:1. Ju mund të kontrolloni raportin e aspektit dhe madhësinë e imazhit të daljes duke përdorur fushat aspect_ratio dhe image_size nën response_format kur type është vendosur në "image" .
Python
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=prompt,
response_format={
"type": "image",
"aspect_ratio": "16:9",
"image_size": "2K",
},
)
JavaScript
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: prompt,
response_format: {
type: "image",
aspect_ratio: "16:9",
image_size: "2K",
},
});
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("image"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "gemini-3.1-flash-image",
"input": "Create a picture of a nano banana dish in a fancy restaurant with a Gemini theme",
"response_format": {
"type": "image",
"aspect_ratio": "16:9",
"image_size": "2K"
}
}'
Raportet e ndryshme të disponueshme dhe madhësia e imazhit të gjeneruar janë renditur në tabelat e mëposhtme:
3.1 Imazh i blicit
| Raporti i aspektit | Rezolucioni 512px | 0.5 mijë tokenë | Rezolucion 1K | 1 mijë tokena | Rezolucion 2K | 2 mijë tokena | Rezolucion 4K | 4K tokena |
|---|---|---|---|---|---|---|---|---|
| 1:1 | 512x512 | 747 | 1024x1024 | 1120 | 2048x2048 | 1680 | 4096x4096 | 2520 |
| 1:4 | 256x1024 | 747 | 512x2048 | 1120 | 1024x4096 | 1680 | 2048x8192 | 2520 |
| 1:8 | 192x1536 | 747 | 384x3072 | 1120 | 768x6144 | 1680 | 1536x12288 | 2520 |
| 2:3 | 424x632 | 747 | 848x1264 | 1120 | 1696x2528 | 1680 | 3392x5056 | 2520 |
| 3:2 | 632x424 | 747 | 1264x848 | 1120 | 2528x1696 | 1680 | 5056x3392 | 2520 |
| 3:4 | 448x600 | 747 | 896x1200 | 1120 | 1792x2400 | 1680 | 3584x4800 | 2520 |
| 4:1 | 1024x256 | 747 | 2048x512 | 1120 | 4096x1024 | 1680 | 8192x2048 | 2520 |
| 4:3 | 600x448 | 747 | 1200x896 | 1120 | 2400x1792 | 1680 | 4800x3584 | 2520 |
| 4:5 | 464x576 | 747 | 928x1152 | 1120 | 1856x2304 | 1680 | 3712x4608 | 2520 |
| 5:4 | 576x464 | 747 | 1152x928 | 1120 | 2304x1856 | 1680 | 4608x3712 | 2520 |
| 8:1 | 1536x192 | 747 | 3072x384 | 1120 | 6144x768 | 1680 | 12288x1536 | 2520 |
| 9:16 | 384x688 | 747 | 768x1376 | 1120 | 1536x2752 | 1680 | 3072x5504 | 2520 |
| 16:9 | 688x384 | 747 | 1376x768 | 1120 | 2752x1536 | 1680 | 5504x3072 | 2520 |
| 21:9 | 792x168 | 747 | 1584x672 | 1120 | 3168x1344 | 1680 | 6336x2688 | 2520 |
Imazh 3.1 Pro
| Raporti i aspektit | Rezolucion 1K | 1 mijë tokena | Rezolucion 2K | 2 mijë tokena | Rezolucion 4K | 4K tokena |
|---|---|---|---|---|---|---|
| 1:1 | 1024x1024 | 1120 | 2048x2048 | 1120 | 4096x4096 | 2000 |
| 2:3 | 848x1264 | 1120 | 1696x2528 | 1120 | 3392x5056 | 2000 |
| 3:2 | 1264x848 | 1120 | 2528x1696 | 1120 | 5056x3392 | 2000 |
| 3:4 | 896x1200 | 1120 | 1792x2400 | 1120 | 3584x4800 | 2000 |
| 4:3 | 1200x896 | 1120 | 2400x1792 | 1120 | 4800x3584 | 2000 |
| 4:5 | 928x1152 | 1120 | 1856x2304 | 1120 | 3712x4608 | 2000 |
| 5:4 | 1152x928 | 1120 | 2304x1856 | 1120 | 4608x3712 | 2000 |
| 9:16 | 768x1376 | 1120 | 1536x2752 | 1120 | 3072x5504 | 2000 |
| 16:9 | 1376x768 | 1120 | 2752x1536 | 1120 | 5504x3072 | 2000 |
| 21:9 | 1584x672 | 1120 | 3168x1344 | 1120 | 6336x2688 | 2000 |
Imazh Flash i Gemini 2.5
| Raporti i aspektit | Rezolucioni | Tokenat |
|---|---|---|
| 1:1 | 1024x1024 | 1290 |
| 2:3 | 832x1248 | 1290 |
| 3:2 | 1248x832 | 1290 |
| 3:4 | 864x1184 | 1290 |
| 4:3 | 1184x864 | 1290 |
| 4:5 | 896x1152 | 1290 |
| 5:4 | 1152x896 | 1290 |
| 9:16 | 768x1344 | 1290 |
| 16:9 | 1344x768 | 1290 |
| 21:9 | 1536x672 | 1290 |
Përzgjedhja e modelit
Zgjidhni modelin që i përshtatet më së miri rastit tuaj specifik të përdorimit.
Gemini 3.1 Flash Image (Nano Banana 2) duhet të jetë modeli juaj i preferuar për gjenerimin e imazheve, si performanca dhe inteligjenca më e mirë në të gjitha aspektet, si dhe balanca e kostos dhe vonesës. Shikoni faqen e çmimeve dhe aftësive të modelit për më shumë detaje.
Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) është modeli më efikas në familjen e gjenerimit të imazheve, duke ofruar vonesë ultra të ulët dhe gjenerim dhe redaktim imazhesh me kosto efektive. Kontrolloni faqen e çmimeve dhe aftësive të modelit për më shumë detaje.
Gemini 3 Pro Image (Nano Banana Pro) është projektuar për prodhimin profesional të aseteve dhe udhëzimeve komplekse. Ky model përmban tokëzim në botën reale duke përdorur Kërkimin në Google, një proces të parazgjedhur "Thinking" që përsos kompozimin para gjenerimit dhe mund të gjenerojë imazhe me rezolucion deri në 4K. Kontrolloni faqen e çmimeve dhe aftësive të modelit për më shumë detaje.
Imazh Flash Gemini 2.5 (Nano Banana) është projektuar për shpejtësi dhe efikasitet. Ky model është i optimizuar për detyra me volum të lartë dhe me vonesë të ulët dhe gjeneron imazhe me rezolucion 1024px. Kontrolloni faqen e çmimeve dhe aftësive të modelit për më shumë detaje.
Kur të përdoret Imagen
Përveç përdorimit të aftësive të integruara të gjenerimit të imazheve të Gemini, mund të hyni edhe në Imagen , modelin tonë të specializuar të gjenerimit të imazheve, përmes API-t Gemini. Planifikoni të migroni para datës së mbylljes.
Çfarë vjen më pas
- Shikoni udhëzuesin Veo për të mësuar se si të gjeneroni video me Gemini API.
- Për të mësuar më shumë rreth modeleve Gemini, shihni modelet Gemini .
Gjenerimi i imazhit Nano Banana
Gjeneruar nga Nano Banana 2 Pyetje: "Një foto e një kopertine me shkëlqim reviste, kopertina minimale blu ka fjalët e mëdha të trasha Nano Banana. Teksti është me shkronja serif dhe mbush pamjen. Asnjë tekst tjetër. Përpara tekstit ka një portret të një personi me një fustan elegant dhe minimalist. Ajo mban me shaka numrin 2, i cili është pika qendrore."
Vendos numrin e botimit dhe datën "Shkurt 2026" në cep së bashku me një barkod. Revista është në një raft pranë një muri të suvatuar me portokalli, brenda një dyqani firmash.Gjeneruar nga Nano Banana Pro Nxitje: "Paraqitni një skenë të qartë, 45° nga lart poshtë, vizatimore 3D miniaturë izometrike të Londrës, duke paraqitur monumentet dhe elementët e saj arkitektonikë më ikonikë. Përdorni tekstura të buta dhe të rafinuara me materiale realiste PBR dhe ndriçim dhe hije të buta dhe të gjalla. Integroni kushtet aktuale të motit direkt në mjedisin e qytetit për të krijuar një atmosferë atmosferike gjithëpërfshirëse. Përdorni një kompozim të pastër dhe minimalist me një sfond të butë me ngjyra të forta. Në qendër të sipërme, vendosni titullin "Londër" me tekst të madh të trashë, një ikonë të spikatur moti poshtë tij, pastaj datën (tekst i vogël) dhe temperaturën (tekst mesatar). I gjithë teksti duhet të jetë i qendërzuar me hapësira të qëndrueshme dhe mund të mbivendoset lehtë me majat e ndërtesave."Gjeneruar nga Nano Banana 2 Njoftim: "Përdorni kërkimin e imazheve për të gjetur imazhe të sakta të një zogu të shkëlqyer ketzal. Krijoni një sfond të bukur 3:2 të këtij zogu, me një gradient natyral nga lart poshtë dhe kompozim minimal."Gjeneruar nga Nano Banana Pro Nxitje: "Vendoseni këtë logo në një reklamë luksoze për një parfum me aromë bananeje. Logoja është integruar në mënyrë të përkryer në shishe."Gjeneruar nga Nano Banana Pro Njoftim: "Një foto e një skene të përditshme në një kafene të mbushur me njerëz që shërben mëngjes. Në plan të parë është një burrë anime me flokë blu, njëri prej personave është një skicues me laps, një tjetër është një person që punon me argjilë"Gjeneruar nga Nano Banana Pro Njoftim: "Përdorni kërkimin për të gjetur se si është pritur lançimi i Gemini 3 Flash. Përdorni këtë informacion për të shkruar një artikull të shkurtër rreth tij (me tituj). Ktheni një foto të artikullit ashtu siç u shfaq në një revistë me shkëlqim të fokusuar në dizajn. Është një foto e një faqeje të vetme të palosur, që tregon artikullin rreth Gemini 3 Flash. Një foto kryesore. Titulli është me serif."Gjeneruar nga Nano Banana Pro Njoftim: "Një ikonë që përfaqëson një qen të lezetshëm. Sfondi është i bardhë. Krijoni ikonat në një stil 3D shumëngjyrësh dhe të prekshëm. Pa tekst."Gjeneruar nga Nano Banana 2 Nxitje: "Bëni një foto që është në mënyrë perfekte izometrike. Nuk është një miniaturë, është një foto e kapur që rastësisht është në mënyrë perfekte izometrike. Është një foto e një kopshti të bukur modern. Ka një pishinë të madhe në formë 2 dhe fjalët: Nano Banana 2."
Nano Banana është emri për aftësitë e gjenerimit të imazheve native të Gemini. Gemini mund të gjenerojë dhe përpunojë imazhe në mënyrë bisedore me tekst, imazhe, video ose një kombinim. Kjo ju lejon të krijoni, modifikoni dhe përsërisni pamjet me një kontroll të paparë.
Nano Banana i referohet katër modeleve të dallueshme të disponueshme në Gemini API:
- Nano Banana 2 Lite ( Gemini 3.1 Flash Lite Image ) (
gemini-3.1-flash-lite-image): Modeli ynë më i shpejtë dhe më i lirë i imazhit Gemini, i projektuar për shpejtësi dhe shkallë ku shpejtësia dhe kostoja janë kufizimet kryesore operative. Nuk është optimizuar për hyrje të shumëfishta referimi ose redaktim sekuencial me shumë kthesa. - Nano Banana 2 ( Gemini 3.1 Flash Image ) (
gemini-3.1-flash-image): Shërben si modeli më i gjithanshëm, modeli më i fuqishëm për të gjitha detyrat. Ai balancon shpejtësinë me gjenerimin e teknologjisë së fundit 4K, njohuritë botërore dhe interpretimin e besueshëm të tekstit. Shkëlqyeshëm në përpunimin dhe qëndrueshmërinë e imazheve me referencë të shumëfishtë. - Nano Banana Pro ( Gemini 3 Pro Image ) (
gemini-3-pro-image): Zgjedhja premium për detyrat më komplekse vizuale, duke ofruar nivelin më të lartë të njohurive botërore, lokalizim të përparuar, qëndrueshmëri të saktë të markës dhe kontroll krijues preciz. - Nano Banana ( Gemini 2.5 Flash Image ) (
gemini-2.5-flash-image): Pionieri i trashëguar i serisë Nano Banana. Ndërsa ka qenë një kalë pune i besueshëm, ne u rekomandojmë fuqimisht klientëve të kalojnë në Nano Banana 2 Lite për të përjetuar cilësi të përmirësuar, shpejtësi më të larta gjenerimi dhe çmime më të ulëta të API-t.
Të gjitha imazhet e gjeneruara përfshijnë një filigran SynthID .
Gjenerimi i imazhit (tekst-në-imazh)
Python
from google import genai
from PIL import Image
import base64
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input="Create a picture of a nano banana dish in a fancy restaurant with a Gemini theme",
)
with open("generated_image.png", "wb") as f:
f.write(base64.b64decode(interaction.output_image.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const prompt =
"Create a picture of a nano banana dish in a fancy restaurant with a Gemini theme";
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: prompt,
});
const generatedImage = interaction.output_image;
if (generatedImage) {
const buffer = Buffer.from(generatedImage.data, "base64");
fs.writeFileSync("gemini-native-image.png", buffer);
console.log("Image saved as gemini-native-image.png");
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("base64"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": [
{"type": "text", "text": "Create a picture of a nano banana dish in a fancy restaurant with a Gemini theme"}
]
}'
Mund të merrni të dhënat e gjeneruara të imazhit duke përdorur vetinë interaction.output_image , e cila kthen bllokun e fundit të gjeneruar të imazhit. Për detaje mbi vetitë e komoditetit, shihni përmbledhjen e Ndërveprimeve .
Redaktimi i imazhit (tekst dhe imazh në imazh)
Reminder : Make sure you have the necessary rights to any images you upload. Don't generate content that infringe on others' rights, including videos or images that deceive, harass, or harm. Your use of this generative AI service is subject to our Prohibited Use Policy .
Provide an image and use text prompts to add, remove, or modify elements, change the style, or adjust the color grading.
The following example demonstrates uploading base64 encoded images. For multiple images, larger payloads, and supported MIME types, check the Image understanding page.
Python
from google import genai
from PIL import Image
import base64
client = genai.Client()
with open("/path/to/cat_image.png", "rb") as f:
image_bytes = f.read()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=[
{
"type": "text",
"text": "Create a picture of a nano banana dish in a fancy restaurant with a Gemini theme"
},
{
"type": "image",
"data": base64.b64encode(image_bytes).decode('utf-8'),
"mime_type": "image/png"
}
],
)
with open("generated_image.png", "wb") as f:
f.write(base64.b64decode(interaction.output_image.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const imagePath = "path/to/cat_image.png";
const imageData = fs.readFileSync(imagePath);
const base64Image = imageData.toString("base64");
const prompt = [
{ type: "text", text: "Create a picture of my cat eating a nano-banana in a" +
"fancy restaurant under the Gemini constellation" },
{
type: "image",
mime_type: "image/png",
data: base64Image
},
];
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: prompt,
});
const generatedImage = interaction.output_image;
if (generatedImage) {
const buffer = Buffer.from(generatedImage.data, "base64");
fs.writeFileSync("gemini-native-image.png", buffer);
console.log("Image saved as gemini-native-image.png");
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Create a picture of my cat eating a nano-banana in a"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d "{
\"model\": \"gemini-3.1-flash-image\",
\"input\": [
{\"type\": \"text\", \"text\": \"Create a picture of my cat eating a nano-banana in a fancy restaurant under the Gemini constellation\"},
{
\"type\": \"image\",
\"mime_type\": \"image/jpeg\",
\"data\": \"<BASE64_IMAGE_DATA>\"
}
]
}"
Multi-turn image editing
Keep generating and editing images conversationally. Multi-turn conversation is the recommended way to iterate on images. The following example shows a prompt to generate an infographic about photosynthesis.
Python
from google import genai
import base64
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input="Create a vibrant infographic that explains photosynthesis as if it were a recipe for a plant's favorite food. Show the \"ingredients\" (sunlight, water, CO2) and the \"finished dish\" (sugar/energy). The style should be like a page from a colorful kids' cookbook, suitable for a 4th grader.",
tools=[{"type": "google_search"}],
)
with open("photosynthesis.png", "wb") as f:
f.write(base64.b64decode(interaction.output_image.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
const ai = new GoogleGenAI({});
async function main() {
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "Create a vibrant infographic that explains photosynthesis as if it were a recipe for a plant's favorite food. Show the \"ingredients\" (sunlight, water, CO2) and the \"finished dish\" (sugar/energy). The style should be like a page from a colorful kids' cookbook, suitable for a 4th grader.",
tools: [{"type": "google_search"}],
});
const generatedImage = interaction.output_image;
if (generatedImage) {
const buffer = Buffer.from(generatedImage.data, "base64");
fs.writeFileSync("photosynthesis.png", buffer);
console.log("Image saved as photosynthesis.png");
}
}
await main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Create a vibrant infographic that explains photosynthesis as if it were a recipe for a plant"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": [
{"type": "text", "text": "Create a vibrant infographic that explains photosynthesis as if it were a recipe for a plants favorite food. Show the \"ingredients\" (sunlight, water, CO2) and the \"finished dish\" (sugar/energy). The style should be like a page from a colorful kids cookbook, suitable for a 4th grader."}
],
"tools": [{"type": "google_search"}]
}'
You can then use the previous_interaction_id to change the language on the graphic to Spanish.
Python
interaction_2 = client.interactions.create(
model="gemini-3.1-flash-image",
input="Update this infographic to be in Spanish. Do not change any other elements of the image.",
previous_interaction_id=interaction.id,
response_format={
"type": "image",
"mime_type": "image/jpeg",
"aspect_ratio": "16:9",
"image_size": "2K"
},
)
generated_image = interaction_2.output_image
if generated_image:
with open("photosynthesis_spanish.png", "wb") as f:
f.write(base64.b64decode(generated_image.data))
JavaScript
const interaction2 = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "Update this infographic to be in Spanish. Do not change any other elements of the image.",
previous_interaction_id: interaction.id,
response_format: {
type: "image",
mime_type: "image/png",
aspect_ratio: "16:9",
image_size: "2K"
},
});
const generatedImage = interaction2.output_image;
if (generatedImage) {
const buffer = Buffer.from(generatedImage.data, "base64");
fs.writeFileSync("photosynthesis_spanish.png", buffer);
}
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Update this infographic to be in Spanish. Do not change any other elements of the image."))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "gemini-3.1-flash-image",
"input": "Update this infographic to be in Spanish. Do not change any other elements of the image.",
"previous_interaction_id": "<PREVIOUS_INTERACTION_ID>",
"response_format": {
"type": "image",
"mime_type": "image/jpeg",
"aspect_ratio": "16:9",
"image_size": "2K"
}
}'
New with Gemini 3 image models
Gemini 3 offers state-of-the-art image generation and editing models. Gemini 3.1 Flash Image is optimized for speed and high-volume use-cases, and Gemini 3 Pro Image is optimized for professional asset production. Designed to tackle the most challenging workflows through advanced reasoning, they excel at complex, multi-turn creation and modification tasks.
- High-resolution output : Built-in generation capabilities for 1K, 2K, and 4K visuals.
- Gemini 3.1 Flash Image adds the smaller 512px (0.5K) resolution.
- Gemini 3.1 Flash Lite Image only supports 1K resolution.
- Advanced text rendering : Capable of generating legible, stylized text for infographics, menus, diagrams, and marketing assets.
- Grounding with Google Search : The model can use Google Search as a tool to verify facts and generate imagery based on real-time data (eg, current weather maps, stock charts, recent events).
- Not supported by Gemini 3.1 Flash Lite Image model.
- Gemini 3.1 Flash Image adds the integration of Google Image Search Grounding alongside Web Search.
- Thinking mode : The model utilizes a "thinking" process to reason through complex prompts. It generates interim "thought images" (visible in the backend but not charged) to refine the composition before producing the final high-quality output.
- Up to 14 reference images : You can now mix up to 14 reference images to produce the final image.
- New aspect ratios : Gemini 3.1 Flash Lite Image adds
1:1,3:2,2:3,3:4,4:3,4:5,5:4,9:16,16:9,21:9aspect ratios .
Use up to 14 reference images
Gemini 3 image models let you to mix up to 14 reference images. These 14 images can include the following:
| Gemini 3.1 Flash Lite Image | Gemini 3.1 Flash Image | Gemini 3 Pro Image |
|---|---|---|
| Up to 14 images of objects with high-fidelity to include in the final image | Up to 10 images of objects with high-fidelity to include in the final image | Up to 6 images of objects with high-fidelity to include in the final image |
| N/A | Up to 4 images of characters to maintain character consistency | Up to 5 images of characters to maintain character consistency |
| N/A | N/A | Up to 3 images to be used as style references |
Python
from google import genai
from google.genai import types
from PIL import Image
import base64
prompt = "An office group photo of these people, they are making funny faces."
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=[
{
"type": "text",
"text": prompt,
},
{
"type": "image",
"data": base64.b64encode(image_bytes).decode('utf-8'),
"mime_type": "image/png"
},
{
"type": "image",
"data": base64.b64encode(image_bytes).decode('utf-8'),
"mime_type": "image/png"
},
{
"type": "image",
"data": base64.b64encode(image_bytes).decode('utf-8'),
"mime_type": "image/png"
},
{
"type": "image",
"data": base64.b64encode(image_bytes).decode('utf-8'),
"mime_type": "image/png"
},
{
"type": "image",
"data": base64.b64encode(image_bytes).decode('utf-8'),
"mime_type": "image/png"
},
],
response_format={
"type": "image",
"aspect_ratio": "5:4",
"image_size": "2K"
},
)
with open("office.png", "wb") as f:
f.write(base64.b64decode(interaction.output_image.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const input = [
{
type: "text",
text: "An office group photo of these people, they are making funny faces.",
},
{ type: "image", mime_type: "image/jpeg", data: base64ImageFile1 },
{ type: "image", mime_type: "image/jpeg", data: base64ImageFile2 },
{ type: "image", mime_type: "image/jpeg", data: base64ImageFile3 },
{ type: "image", mime_type: "image/jpeg", data: base64ImageFile4 },
{ type: "image", mime_type: "image/jpeg", data: base64ImageFile5 },
];
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: input,
response_format: {
type: "image",
aspect_ratio: "5:4",
image_size: "2K",
},
});
const buffer = Buffer.from(interaction.output_image.data, 'base64');
fs.writeFileSync('office.png', buffer);
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("An office group photo of these people, they are making funny faces."))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d "{
\"model\": \"gemini-3.1-flash-image\",
\"input\": [
{\"type\": \"text\", \"text\": \"An office group photo of these people, they are making funny faces.\"},
{\"type\": \"image\", \"mime_type\": \"image/png\", \"data\": \"<BASE64_DATA_IMG_1>\"},
{\"type\": \"image\", \"mime_type\": \"image/png\", \"data\": \"<BASE64_DATA_IMG_2>\"},
{\"type\": \"image\", \"mime_type\": \"image/png\", \"data\": \"<BASE64_DATA_IMG_3>\"},
{\"type\": \"image\", \"mime_type\": \"image/png\", \"data\": \"<BASE64_DATA_IMG_4>\"},
{\"type\": \"image\", \"mime_type\": \"image/png\", \"data\": \"<BASE64_DATA_IMG_5>\"}
],
\"response_format\": {
\"type\": \"image\",
\"aspect_ratio\": \"5:4\",
\"image_size\": \"2K\"
}
}"
Bazë me Kërkimin në Google
Use the Google Search tool to generate images based on real-time information, such as weather forecasts, stock charts, or recent events.
Note that when using Grounding with Google Search with image generation, image-based search results are not passed to the generation model and are excluded from the response (see Grounding with Google Image Search )
Python
from google import genai
from google.genai import types
import base64
prompt = "Visualize the current weather forecast for the next 5 days in San Francisco as a clean, modern weather chart. Add a visual on what I should wear each day"
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=prompt,
tools=[{"type": "google_search"}],
response_format={
"type": "image",
"mime_type": "image/jpeg",
"aspect_ratio": "16:9"
},
)
with open("weather.png", "wb") as f:
f.write(base64.b64decode(interaction.output_image.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "Visualize the current weather forecast for the next 5 days in San Francisco as a clean, modern weather chart. Add a visual on what I should wear each day",
tools: [{"type": "google_search"}],
response_format: {
type: "image",
mime_type: "image/png",
aspect_ratio: "16:9",
image_size: "2K"
},
});
const buffer = Buffer.from(interaction.output_image.data, 'base64');
fs.writeFileSync('weather.png', buffer);
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Visualize the current weather forecast for the next 5 days in San Francisco as a clean, modern weather chart. Add a visual on what I should wear each day"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": [
{"type": "text", "text": "Visualize the current weather forecast for the next 5 days in San Francisco as a clean, modern weather chart. Add a visual on what I should wear each day"}
],
"tools": [{"type": "google_search"}],
"response_format": {
"type": "image",
"mime_type": "image/jpeg",
"aspect_ratio": "16:9"
}
}'
The response includes google_search_call and google_search_result steps, along with inline url_citation annotations on the text step:
-
google_search_result: Containssearch_suggestions, an HTML snippet for rendering search suggestions in your UI. -
url_citationannotations : Inline citations on the text step linking parts of the response to their web sources.
Grounding with Google Search for images (3.1 Flash)
Grounding with Google Image Search allows models to use web images retrieved via Google Image Search as visual context for image generation. Image Search is a new search type within the existing Grounding with Google Search tool, functioning alongside standard Web Search .
To enable Image Search, configure the google_search tool in your API request and specify image_search within the search_types array. Image Search can be used independently or together with Web Search.
Python
from google import genai
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input="A detailed painting of a Timareta butterfly resting on a flower",
tools=[{
"type": "google_search",
"search_types": ["web_search", "image_search"]
}]
)
JavaScript
import { GoogleGenAI } from "@google/genai";
async function main() {
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "A detailed painting of a Timareta butterfly resting on a flower",
tools: [{
"type": "google_search",
"search_types": ["web_search", "image_search"]
}]
});
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("A detailed painting of a Timareta butterfly resting on a flower"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": "A detailed painting of a Timareta butterfly resting on a flower",
"tools": [{"type": "google_search", "search_types": ["web_search", "image_search"]}]
}'
Display requirements
When you use Image Search within Grounding with Google Search, you must display the search_suggestions from the google_search_result step. Full usage requirements are detailed in the Terms of Service .
Përgjigje
For grounded responses using image search, the API returns inline citations and attribution metadata as part of the response steps:
url_citationannotations : Inline citations on the text content block withinmodel_output, linking the generated content to its source.google_search_result: Containssearch_suggestions, an HTML snippet for rendering search suggestions in your UI.
Video-to-image generation (3.1 Flash and 3.1 Flash Lite)
Video-to-image generation allows you to generate new images using a video's context as a multimodal reference. This is useful for creating high-quality video thumbnails, cinematic posters, summary infographics, or new artwork inspired by a video scene.
During generation, the model analyzes the video frames in context to extract visual themes and key events, then uses them alongside your text prompt to synthesize the output image.
You can pass public YouTube URLs directly in your API request or upload local video files using the Files API .
Python
from google import genai
from google.genai import types
import base64
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=[
{
"type": "video",
"uri": "https://www.youtube.com/watch?v=UTdfxFyOQTI",
"mime_type": "video/mp4"
},
{"type": "text", "text": "Generate a poster image that captures the key themes of this video."}
],
response_format={"type": "image", "aspect_ratio": "16:9"}
)
# Save the generated image part
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("video_poster.png", "wb") as f:
f.write(base64.b64decode(content_block.data))
print("Image saved as video_poster.png")
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: [
{
type: "video",
uri: "https://www.youtube.com/watch?v=UTdfxFyOQTI",
mime_type: "video/mp4"
},
{ type: "text", text: "Generate a poster image that captures the key themes of this video." }
],
response_format: {
type: "image",
aspect_ratio: "16:9"
}
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("video_poster.png", buffer);
console.log("Image saved as video_poster.png");
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Generate a poster image that captures the key themes of this video."))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "gemini-3.1-flash-image",
"input": [
{
"type": "video",
"uri": "https://www.youtube.com/watch?v=UTdfxFyOQTI",
"mime_type": "video/mp4"
},
{
"type": "text",
"text": "Generate a poster image that captures the key themes of this video."
}
],
"response_format": {
"type": "image",
"aspect_ratio": "16:9"
}
}'
Generate images up to 4K resolution
Gemini 3 image models generate 1K images by default but can also output 2K, 4K, and 512px (05.K) (Gemini 3.1 Flash Image only) images. To generate higher resolution assets, specify the image_size in the response_format .
You must use an uppercase 'K' (eg 512px (05.K), 1K, 2K, 4K). Lowercase parameters (eg, 1k) will be rejected.
Python
from google import genai
from google.genai import types
import base64
prompt = "Da Vinci style anatomical sketch of a dissected Monarch butterfly. Detailed drawings of the head, wings, and legs on textured parchment with notes in English."
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=prompt,
response_format={
"type": "image",
"mime_type": "image/jpeg",
"aspect_ratio": "1:1",
"image_size": "1K"
},
)
print(interaction.output_text)
with open("butterfly.png", "wb") as f:
f.write(base64.b64decode(interaction.output_image.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "Da Vinci style anatomical sketch of a dissected Monarch butterfly. Detailed drawings of the head, wings, and legs on textured parchment with notes in English.",
response_format: {
type: "image",
mime_type: "image/png",
aspect_ratio: "1:1",
image_size: "1K",
},
});
console.log(interaction.output_text);
const buffer = Buffer.from(interaction.output_image.data, 'base64');
fs.writeFileSync('butterfly.png', buffer);
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Da Vinci style anatomical sketch of a dissected Monarch butterfly. Detailed drawings of the head, wings, and legs on textured parchment with notes in English."))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": "Da Vinci style anatomical sketch of a dissected Monarch butterfly. Detailed drawings of the head, wings, and legs on textured parchment with notes in English.",
"response_format": {
"type": "image",
"mime_type": "image/jpeg",
"aspect_ratio": "1:1",
"image_size": "1K"
}
}'
The following is an example image generated from this prompt:
Thinking process
Gemini 3 image models are thinking models that use a reasoning process ("Thinking") for complex prompts. This feature is enabled by default and cannot be disabled in the API. To learn more about the thinking process, see the Gemini Thinking guide.
The model generates up to two interim images to test composition and logic. The last image within Thinking is also the final rendered image.
You can check the thoughts that lead to the final image being produced.
Python
for step in interaction.steps:
if step.type == "thought":
for content_block in step.summary:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
image = Image.open(io.BytesIO(base64.b64decode(content_block.data)))
image.show()
JavaScript
for (const step of interaction.steps) {
if (step.type === "thought") {
for (const contentBlock of step.summary) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, 'base64');
fs.writeFileSync('thought_image.png', buffer);
}
}
}
}
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.8-flash"))
.input(InteractionsInput.of("Image operation"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
Interleaved text and images
While standard image generation models only output images, some advanced Gemini 3 models (such as gemini-3-pro-image ) can generate interleaved content—like stories or instructional guides containing both text blocks and illustrations inside the same response.
Because the output is complex and interleaved, convenience properties like .output_image or .output_text will not capture the full sequence. To access and save interleaved content, you must manually iterate over steps :
Python
interaction = client.interactions.create(
model="gemini-3-pro-image",
input="Write the story of the lifecycle of a monarch butterfly, interleave illustrations",
)
image_counter = 1
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
filename = f"butterfly_lifecycle_{image_counter}.png"
with open(filename, "wb") as f:
f.write(base64.b64decode(content_block.data))
print(f"\n[Saved illustration: {filename}]\n")
image_counter += 1
JavaScript
const interaction = await ai.interactions.create({
model: "gemini-3-pro-image",
input: "Write the story of the lifecycle of a monarch butterfly, interleave illustrations",
});
let imageCounter = 1;
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
const filename = `butterfly_lifecycle_${imageCounter}.png`;
fs.writeFileSync(filename, buffer);
console.log(`\n[Saved illustration: ${filename}]\n`);
imageCounter++;
}
}
}
}
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3-pro-image"))
.input(InteractionsInput.of("Write the story of the lifecycle of a monarch butterfly, interleave illustrations"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
Controlling thinking levels
With Gemini 3.1 Flash Image and Gemini 3.1 Flash Lite Image, you can control the amount of thinking the model uses to balance quality and latency. The default thinking_level is minimal , and the supported levels are minimal and high .
Python
from google import genai
from PIL import Image
import base64
import io
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input="A futuristic city built inside a giant glass bottle floating in space",
generation_config={"thinking_level": "high"},
)
print(interaction.output_text)
image = Image.open(io.BytesIO(base64.b64decode(interaction.output_image.data)))
image.show()
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "A futuristic city built inside a giant glass bottle floating in space",
generation_config: { thinking_level: "high" },
});
console.log(interaction.output_text);
const buffer = Buffer.from(interaction.output_image.data, 'base64');
fs.writeFileSync('image.png', buffer);
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("A futuristic city built inside a giant glass bottle floating in space"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": "A futuristic city built inside a giant glass bottle floating in space",
"generation_config": {
"thinking_level": "high"
}
}'
Note that thinking tokens are billed by default for thinking models, as the thinking process always happens by default whether you view the process or not.
Other image generation modes
Although Nano Banana image generation models are recommended for most use cases, you can also explore dedicated image generation models:
- Imagen : Google's text-to-image models optimized for generating high-quality images.
- Veo : Google's video generation model.
Generate images in batch
All of the image generation capabilities described on this page can also be run as batch jobs using the Batch API , which is ideal if you need to generate many images.You get higher rate limits in exchange for a turnaround of up to 24 hours.
Prompting guide and strategies
This section provides prompt examples and templates for common image generation and editing workflows. Each example includes a re-usable template and a sample prompt for the Interactions API.
Prompts for generating images
The following examples show how to use text prompts to generate various types of images.
1. Photorealistic scenes
Describe a scene in rich detail. The more specific you are, the more control you have over the results.
Shabllon
A photorealistic [type of shot] of a [subject description] in a [setting
description]. [Description of the light]. Shot from a [camera angle]
with a [lens type].
Prompt
A photorealistic wide-angle shot of a vibrant coral reef teeming with tropical fish. Crystal-clear turquoise water with sunbeams filtering down from the surface, illuminating a sea turtle gliding gracefully over the coral. Shot from a low perspective with a wide-angle lens. Aspect ratio 16:9.
Python
from google import genai
from google.genai import types
import base64
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input="A photorealistic wide-angle shot of a vibrant coral reef teeming with tropical fish. Crystal-clear turquoise water with sunbeams filtering down from the surface, illuminating a sea turtle gliding gracefully over the coral. Shot from a low perspective with a wide-angle lens. Aspect ratio 16:9.",
response_format=[
{
"type": "image",
"mime_type": "image/jpeg",
"aspect_ratio": "16:9",
}
],
)
print(interaction.output_text)
with open("coral_reef.png", "wb") as f:
f.write(base64.b64decode(interaction.output_image.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "A photorealistic wide-angle shot of a vibrant coral reef teeming with tropical fish. Crystal-clear turquoise water with sunbeams filtering down from the surface, illuminating a sea turtle gliding gracefully over the coral. Shot from a low perspective with a wide-angle lens. Aspect ratio 16:9.",
response_format: [
{
type: "image",
mime_type: "image/jpeg",
aspect_ratio: "16:9",
}
],
});
console.log(interaction.output_text);
const buffer = Buffer.from(interaction.output_image.data, 'base64');
fs.writeFileSync('coral_reef.png', buffer);
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("A photorealistic wide-angle shot of a vibrant coral reef teeming with tropical fish. Crystal-clear turquoise water with sunbeams filtering down from the surface, illuminating a sea turtle gliding gracefully over the coral. Shot from a low perspective with a wide-angle lens. Aspect ratio 16:9."))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": "A photorealistic wide-angle shot of a vibrant coral reef teeming with tropical fish. Crystal-clear turquoise water with sunbeams filtering down from the surface, illuminating a sea turtle gliding gracefully over the coral. Shot from a low perspective with a wide-angle lens. Aspect ratio 16:9.",
"response_format": {
"type": "image",
"mime_type": "image/png",
"aspect_ratio": "16:9"
}
}'
2. Stylized illustrations & stickers
Describe the artistic style, subject, and medium. Be specific about the visual detail (bold lines, colors, etc.) for consistent results.
Shabllon
A [style] of a [subject, with details about accessories or actions]
doing [activity]. The design features [visual qualities, e.g., bold outlines,
cel-shading, etc.] and [color/background preference].
Prompt
A kawaii-style sticker of a happy red panda wearing a tiny bamboo hat. It's munching on a green bamboo leaf. The design features bold, clean outlines, simple cel-shading, and a vibrant color palette. The background must be white.
Python
from google import genai
import base64
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input="A kawaii-style sticker of a happy red panda wearing a tiny bamboo hat. It's munching on a green bamboo leaf. The design features bold, clean outlines, simple cel-shading, and a vibrant color palette. The background must be white.",
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("red_panda_sticker.png", "wb") as f:
f.write(base64.b64decode(content_block.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "A kawaii-style sticker of a happy red panda wearing a tiny bamboo hat. It's munching on a green bamboo leaf. The design features bold, clean outlines, simple cel-shading, and a vibrant color palette. The background must be white.",
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("red_panda_sticker.png", buffer);
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("A kawaii-style sticker of a happy red panda wearing a tiny bamboo hat. It"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": "A kawaii-style sticker of a happy red panda wearing a tiny bamboo hat. It is munching on a green bamboo leaf. The design features bold, clean outlines, simple cel-shading, and a vibrant color palette. The background must be white."
}'
3. Accurate text in images
Gemini excels at rendering text. Be clear about the text, the font style (descriptively), and the overall design. Use Gemini 3 Pro Image for professional asset production.
Shabllon
Create a [image type] for [brand/concept] with the text "[text to render]"
in a [font style]. The design should be [style description], with a
[color scheme].
Prompt
Create a modern, minimalist logo for a coffee shop called 'The Daily Grind'. The text should be in a clean, bold, sans-serif font. The color scheme is black and white. Put the logo in a circle. Use a coffee bean in a clever way.
Python
from google import genai
import base64
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input="Create a modern, minimalist logo for a coffee shop called 'The Daily Grind'. The text should be in a clean, bold, sans-serif font. The color scheme is black and white. Put the logo in a circle. Use a coffee bean in a clever way.",
response_format={"type": "image", "aspect_ratio": "1:1"},
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("logo_example.jpg", "wb") as f:
f.write(base64.b64decode(content_block.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "Create a modern, minimalist logo for a coffee shop called 'The Daily Grind'. The text should be in a clean, bold, sans-serif font. The color scheme is black and white. Put the logo in a circle. Use a coffee bean in a clever way.",
response_format: { type: "image", aspect_ratio: "1:1" },
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("logo_example.jpg", buffer);
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Create a modern, minimalist logo for a coffee shop called "))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": "Create a modern, minimalist logo for a coffee shop called The Daily Grind. The text should be in a clean, bold, sans-serif font. The color scheme is black and white. Put the logo in a circle. Use a coffee bean in a clever way.",
"response_format": {
"type": "image",
"aspect_ratio": "1:1"
}
}'
4. Product mockups & commercial photography
Perfect for creating clean, professional product shots for ecommerce, advertising, or branding.
Shabllon
A high-resolution, studio-lit product photograph of a [product description]
on a [background surface/description]. The lighting is a [lighting setup,
e.g., three-point softbox setup] to [lighting purpose]. The camera angle is
a [angle type] to showcase [specific feature]. Ultra-realistic, with sharp
focus on [key detail]. [Aspect ratio].
Prompt
A high-resolution, studio-lit product photograph of a minimalist ceramic
coffee mug in matte black, presented on a polished concrete surface. The
lighting is a three-point softbox setup designed to create soft, diffused
highlights and eliminate harsh shadows. The camera angle is a slightly
elevated 45-degree shot to showcase its clean lines. Ultra-realistic, with
sharp focus on the steam rising from the coffee. Square image.
Python
from google import genai
import base64
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input="A high-resolution, studio-lit product photograph of a minimalist ceramic coffee mug in matte black, presented on a polished concrete surface. The lighting is a three-point softbox setup designed to create soft, diffused highlights and eliminate harsh shadows. The camera angle is a slightly elevated 45-degree shot to showcase its clean lines. Ultra-realistic, with sharp focus on the steam rising from the coffee. Square image.",
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("product_mockup.png", "wb") as f:
f.write(base64.b64decode(content_block.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "A high-resolution, studio-lit product photograph of a minimalist ceramic coffee mug in matte black, presented on a polished concrete surface. The lighting is a three-point softbox setup designed to create soft, diffused highlights and eliminate harsh shadows. The camera angle is a slightly elevated 45-degree shot to showcase its clean lines. Ultra-realistic, with sharp focus on the steam rising from the coffee. Square image.",
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("product_mockup.png", buffer);
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("A high-resolution, studio-lit product photograph of a minimalist ceramic coffee mug in matte black, presented on a polished concrete surface. The lighting is a three-point softbox setup designed to create soft, diffused highlights and eliminate harsh shadows. The camera angle is a slightly elevated 45-degree shot to showcase its clean lines. Ultra-realistic, with sharp focus on the steam rising from the coffee. Square image."))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": "A high-resolution, studio-lit product photograph of a minimalist ceramic coffee mug in matte black, presented on a polished concrete surface. The lighting is a three-point softbox setup designed to create soft, diffused highlights and eliminate harsh shadows. The camera angle is a slightly elevated 45-degree shot to showcase its clean lines. Ultra-realistic, with sharp focus on the steam rising from the coffee. Square image."
}'
5. Minimalist & negative space design
Excellent for creating backgrounds for websites, presentations, or marketing materials where text will be overlaid.
Shabllon
A minimalist composition featuring a single [subject] positioned in the
[bottom-right/top-left/etc.] of the frame. The background is a vast, empty
[color] canvas, creating significant negative space. Soft, subtle lighting.
[Aspect ratio].
Prompt
A minimalist composition featuring a single, delicate red maple leaf
positioned in the bottom-right of the frame. The background is a vast, empty
off-white canvas, creating significant negative space for text. Soft,
diffused lighting from the top left. Square image.
Python
from google import genai
import base64
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input="A minimalist composition featuring a single, delicate red maple leaf positioned in the bottom-right of the frame. The background is a vast, empty off-white canvas, creating significant negative space for text. Soft, diffused lighting from the top left. Square image.",
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("minimalist_design.png", "wb") as f:
f.write(base64.b64decode(content_block.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "A minimalist composition featuring a single, delicate red maple leaf positioned in the bottom-right of the frame. The background is a vast, empty off-white canvas, creating significant negative space for text. Soft, diffused lighting from the top left. Square image.",
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("minimalist_design.png", buffer);
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("A minimalist composition featuring a single, delicate red maple leaf positioned in the bottom-right of the frame. The background is a vast, empty off-white canvas, creating significant negative space for text. Soft, diffused lighting from the top left. Square image."))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": "A minimalist composition featuring a single, delicate red maple leaf positioned in the bottom-right of the frame. The background is a vast, empty off-white canvas, creating significant negative space for text. Soft, diffused lighting from the top left. Square image."
}'
6. Sequential art (comic panel / storyboard)
Builds on character consistency and scene description to create panels for visual storytelling. For accuracy with text and storytelling ability, these prompts work best with Gemini 3 Pro and Gemini 3.1 Flash Image.
Shabllon
Make a 3 panel comic in a [style]. Put the character in a [type of scene].
Prompt
Make a 3 panel comic in a gritty, noir art style with high-contrast black and white inks. Put the character in a humurous scene.
Python
from google import genai
from PIL import Image
import base64
client = genai.Client()
with open('/path/to/your/man_in_white_glasses.jpg', 'rb') as f:
image_bytes = f.read()
text_input = "Make a 3 panel comic in a gritty, noir art style with high-contrast black and white inks. Put the character in a humurous scene."
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=[
{"type": "text", "text": text_input},
{
"type": "image",
"data": base64.b64encode(image_bytes).decode('utf-8'),
"mime_type": "image/jpeg"
}
],
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("comic_panel.jpg", "wb") as f:
f.write(base64.b64decode(content_block.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const imagePath = "/path/to/your/man_in_white_glasses.jpg";
const imageData = fs.readFileSync(imagePath);
const base64Image = imageData.toString("base64");
const input = [
{ type: "text", text: "Make a 3 panel comic in a gritty, noir art style with high-contrast black and white inks. Put the character in a humurous scene." },
{
type: "image",
mime_type: "image/jpeg",
data: base64Image
},
];
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: input,
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("comic_panel.jpg", buffer);
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Make a 3 panel comic in a gritty, noir art style with high-contrast black and white inks. Put the character in a humurous scene."))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": [
{"type": "text", "text": "Make a 3 panel comic in a gritty, noir art style with high-contrast black and white inks. Put the character in a humurous scene."},
{"type": "image", "data": "<BASE64_IMAGE_DATA>", "mime_type": "image/jpeg"}
]
}'
Hyrje | Prodhimi |
| |
7. Grounding with Google Search
Use Google Search to generate images based on recent or real-time information. This is useful for news, weather, and other time-sensitive topics.
Prompt
Make a simple but stylish graphic of last night's Arsenal game in the Champion's League
Python
from google import genai
from google.genai import types
import base64
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input="Make a simple but stylish graphic of last night's Arsenal game in the Champion's League",
tools=[{"type": "google_search"}],
response_format={"type": "image", "aspect_ratio": "16:9"},
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("football-score.jpg", "wb") as f:
f.write(base64.b64decode(content_block.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "Make a simple but stylish graphic of last night's Arsenal game in the Champion's League",
tools: [{ type: "google_search" }],
response_format: { type: "image", aspect_ratio: "16:9", image_size: "2K" },
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("football-score.jpg", buffer);
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Make a simple but stylish graphic of last night"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"input": "Make a simple but stylish graphic of last nights Arsenal game in the Champions League",
"tools": [{"type": "google_search"}],
"response_format": {
"type": "image",
"aspect_ratio": "16:9"
}
}'
Prompts for editing images
These examples show how to provide images alongside your text prompts for editing, composition, and style transfer.
1. Adding and removing elements
Provide an image and describe your change. The model will match the original image's style, lighting, and perspective.
Shabllon
Using the provided image of [subject], please [add/remove/modify] [element]
to/from the scene. Ensure the change is [description of how the change should
integrate].
Prompt
"Using the provided image of my cat, please add a small, knitted wizard hat
on its head. Make it look like it's sitting comfortably and matches the soft
lighting of the photo."
Python
from google import genai
from PIL import Image
import base64
client = genai.Client()
with open('/path/to/your/cat_photo.png', 'rb') as f:
image_bytes = f.read()
text_input = """Using the provided image of my cat, please add a small, knitted wizard hat on its head. Make it look like it's sitting comfortably and not falling off."""
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=[
{"type": "text", "text": text_input},
{
"type": "image",
"data": base64.b64encode(image_bytes).decode('utf-8'),
"mime_type": "image/png"
}
],
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("cat_with_hat.png", "wb") as f:
f.write(base64.b64decode(content_block.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const imagePath = "/path/to/your/cat_photo.png";
const imageData = fs.readFileSync(imagePath);
const base64Image = imageData.toString("base64");
const input = [
{ type: "text", text: "Using the provided image of my cat, please add a small, knitted wizard hat on its head. Make it look like it's sitting comfortably and not falling off." },
{
type: "image",
mime_type: "image/png",
data: base64Image
},
];
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: input,
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("cat_with_hat.png", buffer);
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Using the provided image of my cat, please add a small, knitted wizard hat on its head. Make it look like it"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d "{
\"model\": \"gemini-3.1-flash-image\",
\"input\": [
{\"type\": \"text\", \"text\": \"Using the provided image of my cat, please add a small, knitted wizard hat on its head. Make it look like it's sitting comfortably and not falling off.\"},
{\"type\": \"image\", \"mime_type\":\"image/png\", \"data\": \"<BASE64_IMAGE_DATA>\"}
]
}"
Hyrje | Prodhimi |
| |
2. Inpainting (semantic masking)
Conversationally define a "mask" to edit a specific part of an image while leaving the rest untouched.
Shabllon
Using the provided image, change only the [specific element] to [new
element/description]. Keep everything else in the image exactly the same,
preserving the original style, lighting, and composition.
Prompt
"Using the provided image of a living room, change only the blue sofa to be
a vintage, brown leather chesterfield sofa. Keep the rest of the room,
including the pillows on the sofa and the lighting, unchanged."
Python
from google import genai
from PIL import Image
import base64
client = genai.Client()
with open('/path/to/your/living_room.png', 'rb') as f:
image_bytes = f.read()
text_input = """Using the provided image of a living room, change only the blue sofa to be a vintage, brown leather chesterfield sofa. Keep the rest of the room, including the pillows on the sofa and the lighting, unchanged."""
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=[
{
"type": "image",
"data": base64.b64encode(image_bytes).decode('utf-8'),
"mime_type": "image/png"
},
{"type": "text", "text": text_input}
],
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("living_room_edited.png", "wb") as f:
f.write(base64.b64decode(content_block.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const imagePath = "/path/to/your/living_room.png";
const imageData = fs.readFileSync(imagePath);
const base64Image = imageData.toString("base64");
const input = [
{
type: "image",
mime_type: "image/png",
data: base64Image
},
{ type: "text", text: "Using the provided image of a living room, change only the blue sofa to be a vintage, brown leather chesterfield sofa. Keep the rest of the room, including the pillows on the sofa and the lighting, unchanged." },
];
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: input,
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("living_room_edited.png", buffer);
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Using the provided image of a living room, change only the blue sofa to be a vintage, brown leather chesterfield sofa. Keep the rest of the room, including the pillows on the sofa and the lighting, unchanged."))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d "{
\"model\": \"gemini-3.1-flash-image\",
\"input\": [
{\"type\": \"image\", \"mime_type\":\"image/png\", \"data\": \"<BASE64_IMAGE_DATA>\"},
{\"type\": \"text\", \"text\": \"Using the provided image of a living room, change only the blue sofa to be a vintage, brown leather chesterfield sofa. Keep the rest of the room, including the pillows on the sofa and the lighting, unchanged.\"}
]
}"
Hyrje | Prodhimi |
| |
3. Style transfer
Provide an image and ask the model to recreate its content in a different artistic style.
Shabllon
Transform the provided photograph of [subject] into the artistic style of [artist/art style]. Preserve the original composition but render it with [description of stylistic elements].
Prompt
"Transform the provided photograph of a modern city street at night into the artistic style of Vincent van Gogh's 'Starry Night'. Preserve the original composition of buildings and cars, but render all elements with swirling, impasto brushstrokes and a dramatic palette of deep blues and bright yellows."
Python
from google import genai
from PIL import Image
import base64
client = genai.Client()
with open('/path/to/your/city.png', 'rb') as f:
image_bytes = f.read()
text_input = """Transform the provided photograph of a modern city street at night into the artistic style of Vincent van Gogh's 'Starry Night'. Preserve the original composition of buildings and cars, but render all elements with swirling, impasto brushstrokes and a dramatic palette of deep blues and bright yellows."""
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=[
{
"type": "image",
"data": base64.b64encode(image_bytes).decode('utf-8'),
"mime_type": "image/png"
},
{"type": "text", "text": text_input}
],
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("city_style_transfer.png", "wb") as f:
f.write(base64.b64decode(content_block.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const imageData = fs.readFileSync("/path/to/your/city.png");
const base64Image = imageData.toString("base64");
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: [
{
type: "image",
mime_type: "image/png",
data: base64Image
},
{ type: "text", text: "Transform the provided photograph of a modern city street at night into the artistic style of Vincent van Gogh's 'Starry Night'. Preserve the original composition of buildings and cars, but render all elements with swirling, impasto brushstrokes and a dramatic palette of deep blues and bright yellows." },
],
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("city_style_transfer.png", buffer);
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Transform the provided photograph of a modern city street at night into the artistic style of Vincent van Gogh"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d "{
\"model\": \"gemini-3.1-flash-image\",
\"input\": [
{\"type\": \"image\", \"mime_type\":\"image/png\", \"data\": \"<BASE64_IMAGE_DATA>\"},
{\"type\": \"text\", \"text\": \"Transform the provided photograph of a modern city street at night into the artistic style of Vincent van Gogh's 'Starry Night'. Preserve the original composition of buildings and cars, but render all elements with swirling, impasto brushstrokes and a dramatic palette of deep blues and bright yellows.\"}
]
}"
Hyrje | Prodhimi |
| |
4. Advanced composition: combining multiple images
Provide multiple images as context to create a new, composite scene. This is perfect for product mockups or creative collages.
Shabllon
Create a new image by combining the elements from the provided images. Take
the [element from image 1] and place it with/on the [element from image 2].
The final image should be a [description of the final scene].
Prompt
"Create a professional e-commerce fashion photo. Take the blue floral dress
from the first image and let the woman from the second image wear it.
Generate a realistic, full-body shot of the woman wearing the dress, with
the lighting and shadows adjusted to match the outdoor environment."
Python
from google import genai
from PIL import Image
import base64
client = genai.Client()
with open('/path/to/your/dress.png', 'rb') as f:
dress_bytes = f.read()
with open('/path/to/your/model.png', 'rb') as f:
model_bytes = f.read()
text_input = """Create a professional e-commerce fashion photo. Take the blue floral dress from the first image and let the woman from the second image wear it. Generate a realistic, full-body shot of the woman wearing the dress, with the lighting and shadows adjusted to match the outdoor environment."""
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=[
{
"type": "image",
"data": base64.b64encode(dress_bytes).decode('utf-8'),
"mime_type": "image/png"
},
{
"type": "image",
"data": base64.b64encode(model_bytes).decode('utf-8'),
"mime_type": "image/png"
},
{"type": "text", "text": text_input}
],
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("fashion_ecommerce_shot.png", "wb") as f:
f.write(base64.b64decode(content_block.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const imagePath1 = "/path/to/your/dress.png";
const imageData1 = fs.readFileSync(imagePath1);
const base64Image1 = imageData1.toString("base64");
const imagePath2 = "/path/to/your/model.png";
const imageData2 = fs.readFileSync(imagePath2);
const base64Image2 = imageData2.toString("base64");
const input = [
{
type: "image",
mime_type: "image/png",
data: base64Image1
},
{
type: "image",
mime_type: "image/png",
data: base64Image2
},
{ type: "text", text: "Create a professional e-commerce fashion photo. Take the blue floral dress from the first image and let the woman from the second image wear it. Generate a realistic, full-body shot of the woman wearing the dress, with the lighting and shadows adjusted to match the outdoor environment." },
];
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: input,
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("fashion_ecommerce_shot.png", buffer);
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Create a professional e-commerce fashion photo. Take the blue floral dress from the first image and let the woman from the second image wear it. Generate a realistic, full-body shot of the woman wearing the dress, with the lighting and shadows adjusted to match the outdoor environment."))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d "{
\"model\": \"gemini-3.1-flash-image\",
\"input\": [
{\"type\": \"image\", \"mime_type\":\"image/png\", \"data\": \"<BASE64_IMAGE_DATA_1>\"},
{\"type\": \"image\", \"mime_type\":\"image/png\", \"data\": \"<BASE64_IMAGE_DATA_2>\"},
{\"type\": \"text\", \"text\": \"Create a professional e-commerce fashion photo. Take the blue floral dress from the first image and let the woman from the second image wear it. Generate a realistic, full-body shot of the woman wearing the dress, with the lighting and shadows adjusted to match the outdoor environment.\"}
}]
}"
Input 1 | Input 2 | Prodhimi |
| | |
5. High-fidelity detail preservation
To ensure critical details (like a face or logo) are preserved during an edit, describe them in great detail along with your edit request.
Shabllon
Using the provided images, place [element from image 2] onto [element from
image 1]. Ensure that the features of [element from image 1] remain
completely unchanged. The added element should [description of how the
element should integrate].
Prompt
"Take the first image of the woman with brown hair, blue eyes, and a neutral
expression. Add the logo from the second image onto her black t-shirt.
Ensure the woman's face and features remain completely unchanged. The logo
should look like it's naturally printed on the fabric, following the folds
of the shirt."
Python
from google import genai
from PIL import Image
import base64
client = genai.Client()
with open('/path/to/your/woman.png', 'rb') as f:
woman_bytes = f.read()
with open('/path/to/your/logo.png', 'rb') as f:
logo_bytes = f.read()
text_input = """Take the first image of the woman with brown hair, blue eyes, and a neutral expression. Add the logo from the second image onto her black t-shirt. Ensure the woman's face and features remain completely unchanged. The logo should look like it's naturally printed on the fabric, following the folds of the shirt."""
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=[
{"type": "image", "mime_type":"image/png", "data": base64.b64encode(woman_bytes).decode('utf-8')},
{"type": "image", "mime_type":"image/png", "data": base64.b64encode(logo_bytes).decode('utf-8')},
{"type": "text", "text": text_input}
],
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("woman_with_logo.png", "wb") as f:
f.write(base64.b64decode(content_block.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const imagePath1 = "/path/to/your/woman.png";
const imageData1 = fs.readFileSync(imagePath1);
const base64Image1 = imageData1.toString("base64");
const imagePath2 = "/path/to/your/logo.png";
const imageData2 = fs.readFileSync(imagePath2);
const base64Image2 = imageData2.toString("base64");
const input = [
{"type": "image", "mime_type":"image/png", "data": base64Image1},
{"type": "image", "mime_type":"image/png", "data": base64Image2},
{"type": "text", "text": "Take the first image of the woman with brown hair, blue eyes, and a neutral expression. Add the logo from the second image onto her black t-shirt. Ensure the woman's face and features remain completely unchanged. The logo should look like it's naturally printed on the fabric, following the folds of the shirt."},
];
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: input,
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("woman_with_logo.png", buffer);
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("model_output"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d "{
\"model\": \"gemini-3.1-flash-image\",
\"input\": [
{\"type\": \"image\", \"mime_type\":\"image/png\", \"data\": \"<BASE64_IMAGE_DATA_1>\"},
{\"type\": \"image\", \"mime_type\":\"image/png\", \"data\": \"<BASE64_IMAGE_DATA_2>\"},
{\"type\": \"text\", \"text\": \"Take the first image of the woman with brown hair, blue eyes, and a neutral expression. Add the logo from the second image onto her black t-shirt. Ensure the woman's face and features remain completely unchanged. The logo should look like it's naturally printed on the fabric, following the folds of the shirt.\"}
]
}"
Input 1 | Input 2 | Prodhimi |
| | |
6. Bring something to life
Upload a rough sketch or drawing and ask the model to refine it into a finished image.
Shabllon
Turn this rough [medium] sketch of a [subject] into a [style description]
photo. Keep the [specific features] from the sketch but add [new details/materials].
Prompt
"Turn this rough pencil sketch of a futuristic car into a polished photo of the finished concept car in a showroom. Keep the sleek lines and low profile from the sketch but add metallic blue paint and neon rim lighting."
Python
from google import genai
from PIL import Image
import base64
client = genai.Client()
with open('/path/to/your/car_sketch.png', 'rb') as f:
sketch_bytes = f.read()
text_input = """Turn this rough pencil sketch of a futuristic car into a polished photo of the finished concept car in a showroom. Keep the sleek lines and low profile from the sketch but add metallic blue paint and neon rim lighting."""
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=[
{"type": "image", "mime_type":"image/png", "data": base64.b64encode(sketch_bytes).decode('utf-8')},
{"type": "text", "text": text_input}
],
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("car_photo.png", "wb") as f:
f.write(base64.b64decode(content_block.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
async function main() {
const ai = new GoogleGenAI({});
const imagePath = "/path/to/your/car_sketch.png";
const imageData = fs.readFileSync(imagePath);
const base64Image = imageData.toString("base64");
const input = [
{"type": "image", "mime_type":"image/png", "data": base64Image},
{"type": "text", "text": "Turn this rough pencil sketch of a futuristic car into a polished photo of the finished concept car in a showroom. Keep the sleek lines and low profile from the sketch but add metallic blue paint and neon rim lighting."},
];
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: input,
});
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text") {
console.log(contentBlock.text);
} else if (contentBlock.type === "image") {
const buffer = Buffer.from(contentBlock.data, "base64");
fs.writeFileSync("car_photo.png", buffer);
}
}
}
}
}
main();
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("model_output"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d "{
\"model\": \"gemini-3.1-flash-image\",
\"input\": [
{\"type\": \"image\", \"mime_type\":\"image/png\", \"data\": \"<BASE64_IMAGE_DATA>\"},
{\"type\": \"text\", \"text\": \"Turn this rough pencil sketch of a futuristic car into a polished photo of the finished concept car in a showroom. Keep the sleek lines and low profile from the sketch but add metallic blue paint and neon rim lighting.\"}
]
}"
Hyrje | Prodhimi |
| |
7. Character consistency: 360 view
You can generate 360-degree views of a character by iteratively prompting for different angles. For best results, include previously generated images in subsequent prompts to maintain consistency. For complex poses, include a reference image of the selected pose.
Shabllon
A studio portrait of [person] against [background], [looking forward/in profile looking right/etc.]
Prompt
A studio portrait of this man against white, in profile looking right
Python
from google import genai
from PIL import Image
import base64
client = genai.Client()
with open('/path/to/your/man_in_white_glasses.jpg', 'rb') as f:
image_bytes = f.read()
text_input = """A studio portrait of this man against white, in profile looking right"""
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input={
{"type": "text", "text": text_input},
{"type": "image", "mime_type":"image/png", "data": base64.b64encode(image_bytes).decode('utf-8')}
},
)
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text":
print(content_block.text)
elif content_block.type == "image":
with open("man_right_profile.png", "wb") as f:
f.write(base64.b64decode(content_block.data))
Hyrje | Output 1 | Output 2 |
| | |
Praktikat më të mira
To elevate your results from good to great, incorporate these professional strategies into your workflow.
- Be hyper-specific: The more detail you provide, the more control you have. Instead of "fantasy armor," describe it: "ornate elven plate armor, etched with silver leaf patterns, with a high collar and pauldrons shaped like falcon wings."
- Provide context and intent: Explain the purpose of the image. The model's understanding of context will influence the final output. For example, "Create a logo for a high-end, minimalist skincare brand" will yield better results than just "Create a logo."
- Iterate and refine: Don't expect a perfect image on the first try. Use the conversational nature of the model to make small changes. Follow up with prompts like, "That's great, but can you make the lighting a bit warmer?" or "Keep everything the same, but change the character's expression to be more serious."
- Use step-by-step instructions: For complex scenes with many elements, break your prompt into steps. "First, create a background of a serene, misty forest at dawn. Then, in the foreground, add a moss-covered ancient stone altar. Finally, place a single, glowing sword on top of the altar."
- Use "semantic negative prompts": Instead of saying "no cars," describe the intended scene positively: "an empty, deserted street with no signs of traffic."
- Control the camera: Use photographic and cinematic language to control the composition. Terms like
wide-angle shot,macro shot,low-angle perspective.
Kufizime
- For best performance, use the following languages: EN, ar-EG, de-DE, es-MX, fr-FR, hi-IN, id-ID, it-IT, ja-JP, ko-KR, pt-BR, ru-RU, ua-UA, vi-VN, zh-CN.
- Image generation does not support audio inputs. Video inputs are only supported for Gemini 3.1 Flash Image and Gemini 3.1 Flash Lite Image.
- The model won't always follow the exact number of image outputs that the user explicitly asks for.
-
gemini-2.5-flash-imageworks best with up to 3 images as input, whilegemini-3-pro-imagesupports 5 images with high fidelity, and up to 14 images in total.gemini-3.1-flash-imagesupports character resemblance of up to 4 characters and the fidelity of up to 10 objects in a single workflow. - When generating text for an image, Gemini works best if you first generate the text and then ask for an image with the text.
-
gemini-3.1-flash-imageGrounding with Google Search does not support using real-world images of people from web search at this time. - All generated images include a SynthID watermark .
Optional configurations
You can optionally configure the output format, aspect ratio, and image size using the response_format parameter.
Output format
The model defaults to returning both text and image responses. You can configure the response to return only the generated images (omitting the conversational text) by specifying an image format in the response_format parameter.
To request multiple modalities (for example, both text and the generated image), pass an array of format entries to response_format instead.
Python
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input="Write a short poem about a starry night and generate an image of it.",
response_format=[
{"type": "text"},
{"type": "image"},
],
)
JavaScript
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "Write a short poem about a starry night and generate an image of it.",
response_format: [
{ type: "text" },
{ type: "image" },
],
});
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("Write a short poem about a starry night and generate an image of it."))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "gemini-3.1-flash-image",
"input": "Write a short poem about a starry night and generate an image of it.",
"response_format": [
{ "type": "text" },
{ "type": "image" }
]
}'
Aspect ratios and image size
By default, the model matches the output image size to that of your input image, or otherwise generates 1:1 squares. You can control the aspect ratio and the size of the output image using the aspect_ratio and image_size fields under response_format when type is set to "image" .
Python
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input=prompt,
response_format={
"type": "image",
"aspect_ratio": "16:9",
"image_size": "2K",
},
)
JavaScript
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: prompt,
response_format: {
type: "image",
aspect_ratio: "16:9",
image_size: "2K",
},
});
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
.model(Model.of("gemini-3.1-flash-image"))
.input(InteractionsInput.of("image"))
.build();
var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
PUSHTIM
curl -s -X POST \
"https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "gemini-3.1-flash-image",
"input": "Create a picture of a nano banana dish in a fancy restaurant with a Gemini theme",
"response_format": {
"type": "image",
"aspect_ratio": "16:9",
"image_size": "2K"
}
}'
The different ratios available and the size of the image generated are listed in the following tables:
3.1 Flash Image
| Aspect ratio | 512px resolution | 0.5K tokens | 1K resolution | 1K tokens | 2K resolution | 2K tokens | 4K resolution | 4K tokens |
|---|---|---|---|---|---|---|---|---|
| 1:1 | 512x512 | 747 | 1024x1024 | 1120 | 2048x2048 | 1680 | 4096x4096 | 2520 |
| 1:4 | 256x1024 | 747 | 512x2048 | 1120 | 1024x4096 | 1680 | 2048x8192 | 2520 |
| 1:8 | 192x1536 | 747 | 384x3072 | 1120 | 768x6144 | 1680 | 1536x12288 | 2520 |
| 2:3 | 424x632 | 747 | 848x1264 | 1120 | 1696x2528 | 1680 | 3392x5056 | 2520 |
| 3:2 | 632x424 | 747 | 1264x848 | 1120 | 2528x1696 | 1680 | 5056x3392 | 2520 |
| 3:4 | 448x600 | 747 | 896x1200 | 1120 | 1792x2400 | 1680 | 3584x4800 | 2520 |
| 4:1 | 1024x256 | 747 | 2048x512 | 1120 | 4096x1024 | 1680 | 8192x2048 | 2520 |
| 4:3 | 600x448 | 747 | 1200x896 | 1120 | 2400x1792 | 1680 | 4800x3584 | 2520 |
| 4:5 | 464x576 | 747 | 928x1152 | 1120 | 1856x2304 | 1680 | 3712x4608 | 2520 |
| 5:4 | 576x464 | 747 | 1152x928 | 1120 | 2304x1856 | 1680 | 4608x3712 | 2520 |
| 8:1 | 1536x192 | 747 | 3072x384 | 1120 | 6144x768 | 1680 | 12288x1536 | 2520 |
| 9:16 | 384x688 | 747 | 768x1376 | 1120 | 1536x2752 | 1680 | 3072x5504 | 2520 |
| 16:9 | 688x384 | 747 | 1376x768 | 1120 | 2752x1536 | 1680 | 5504x3072 | 2520 |
| 21:9 | 792x168 | 747 | 1584x672 | 1120 | 3168x1344 | 1680 | 6336x2688 | 2520 |
3.1 Pro Image
| Aspect ratio | 1K resolution | 1K tokens | 2K resolution | 2K tokens | 4K resolution | 4K tokens |
|---|---|---|---|---|---|---|
| 1:1 | 1024x1024 | 1120 | 2048x2048 | 1120 | 4096x4096 | 2000 |
| 2:3 | 848x1264 | 1120 | 1696x2528 | 1120 | 3392x5056 | 2000 |
| 3:2 | 1264x848 | 1120 | 2528x1696 | 1120 | 5056x3392 | 2000 |
| 3:4 | 896x1200 | 1120 | 1792x2400 | 1120 | 3584x4800 | 2000 |
| 4:3 | 1200x896 | 1120 | 2400x1792 | 1120 | 4800x3584 | 2000 |
| 4:5 | 928x1152 | 1120 | 1856x2304 | 1120 | 3712x4608 | 2000 |
| 5:4 | 1152x928 | 1120 | 2304x1856 | 1120 | 4608x3712 | 2000 |
| 9:16 | 768x1376 | 1120 | 1536x2752 | 1120 | 3072x5504 | 2000 |
| 16:9 | 1376x768 | 1120 | 2752x1536 | 1120 | 5504x3072 | 2000 |
| 21:9 | 1584x672 | 1120 | 3168x1344 | 1120 | 6336x2688 | 2000 |
Gemini 2.5 Flash Image
| Aspect ratio | Resolution | Tokenat |
|---|---|---|
| 1:1 | 1024x1024 | 1290 |
| 2:3 | 832x1248 | 1290 |
| 3:2 | 1248x832 | 1290 |
| 3:4 | 864x1184 | 1290 |
| 4:3 | 1184x864 | 1290 |
| 4:5 | 896x1152 | 1290 |
| 5:4 | 1152x896 | 1290 |
| 9:16 | 768x1344 | 1290 |
| 16:9 | 1344x768 | 1290 |
| 21:9 | 1536x672 | 1290 |
Model selection
Choose the model best suited for your specific use case.
Gemini 3.1 Flash Image (Nano Banana 2) should be your go-to image generation model, as the best all around performance and intelligence to cost and latency balance. Check the model pricing and capabilities page for more details.
Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) is the most efficient model in the image generation family, offering ultra-low latency and cost-effective image generation and editing. Check the model pricing and capabilities page for more details.
Gemini 3 Pro Image (Nano Banana Pro) is designed for professional asset production and complex instructions. This model features real-world grounding using Google Search, a default "Thinking" process that refines composition prior to generation, and can generate images of up to 4K resolutions. Check the model pricing and capabilities page for more details.
Gemini 2.5 Flash Image (Nano Banana) is designed for speed and efficiency. This model is optimized for high-volume, low-latency tasks and generates images at 1024px resolution. Check the model pricing and capabilities page for more details.
When to use Imagen
In addition to using Gemini's built-in image generation capabilities, you can also access Imagen , our specialized image generation model, through the Gemini API. Plan to migrate before the shutdown date.
Çfarë vjen më pas
- Check out the Veo guide to learn how to generate videos with the Gemini API.
- To learn more about Gemini models, see Gemini models .