Visual intelligence for your home.
Benchmark LLMs by fighting in Street Fighter 3
Let Claude (or any LLM) actually watch a video
Generate short videos with one click using AI LLM
Uses Qwen3-ASR, local LLM, Whisper, TEN-VAD
"VideoRAG: Chat with Your Videos
All-in-one WebUI for AI generative image and video creation
Generate blog articles from video or audio
The media player for language learning, with dual subtitles
The all-in-one local AI studio for your desktop
Build multimodal language agents for fast prototype and production
Code and models for ICML 2024 paper, NExT-GPT
Data Infrastructure providing an approach to multimodal AI workloads
Search all of YouTube from the command line
From nobody to big model (LLM) hero
Capable of understanding text, audio, vision, video
GPT4V-level open-source multi-modal model based on Llama3-8B
Qwen3-omni is a natively end-to-end, omni-modal LLM
Lightweight Python library for adding real-time multi-object tracking
Qwen3-VL, the multimodal large language model series by Alibaba Cloud
Open Vision Agents by Stream. Build voice and vision agents quickly
My ComfyUI workflows collection
Moonshot's most powerful AI model
Secure open source cloud runtime for AI apps & AI agents
Adversarial Robustness Toolbox (ART) - Python Library for ML security