SSealbook
Sealbook / Open source / Machine learning & data science

Francis-Rings/StableAvatar

[NeurIPS2026] We present StableAvatar, the first end-to-end video diffusion transformer, which synthesizes infinite-length high-quality audio-driven avatar videos without any post-processing, conditioned on a reference image and audio.

aigcavatar-generatorvideo-generation
GitHub โ†—

License & maintenance

MIT is a permissive license: free to use commercially with attribution.

Last code push 24 days ago.

Similar projects

RepositoryStarsLanguageLicenseActivity
1ATH-MaaS/Pixelle-Video๐Ÿš€ AI ๅ…จ่‡ชๅŠจ็Ÿญ่ง†้ข‘ๅผ•ๆ“Ž | AI Fully Automated Short Video Engineโ˜… 29.1kPythonApache-2.0Slowing
2duixcom/Duix-Avatar๐Ÿš€ Truly open-source AI avatar(digital human) toolkit for offline video generation and digital human cloning.โ˜… 16kCOtherSlowing
3openclaw/openclawThe AI that really does things. Any OS. Any Platform. The lobster way. ๐Ÿฆž โ˜… 392.4kTypeScriptMITActive
4tensorflow/tensorflowAn Open Source Machine Learning Framework for Everyoneโ˜… 201.1kC++Apache-2.0Active
5AUTOMATIC1111/stable-diffusion-webuiStable Diffusion web UIโ˜… 165.1kPythonAGPL-3.0Slowing
6Comfy-Org/ComfyUIThe most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the wโ˜… 138.4kPythonGPL-3.0Active
7openai/whisperRobust Speech Recognition via Large-Scale Weak Supervisionโ˜… 110.8kPythonMITActive
8pytorch/pytorchTensors and Dynamic neural networks in Python with strong GPU accelerationโ˜… 104.8kPythonOtherActive