Excited to share our work: StableAvatar It is the first Wan2.1-1.3B-based video diffusion transformer, which synthesizes infinite-length high-quality avatar videos, conditioned on a reference image and audio. Paper: arxiv.org/abs/2508.08248 Code:github.com/Francis-Rings/…

🚀 Check out StableAvatar demo on Hugging Face! 🎭 Audio-driven avatar video generation with just 1 image + 1 audio. 👉 huggingface.co/spaces/Yinming… ⚠️ Due to video generation limits, currently only Hugging Face Pro users can try it out. Thanks Gradio for the awesome interface! 💡

Have you ever seen Professor Snape like this at Hogwarts? With StableAvatar, anything is possible! We’re excited to share brand-new demos synthesized by StableAvatar! Paper: arxiv.org/abs/2508.08248 Code:github.com/Francis-Rings/…

Excited to share our work: FlashPortrait It is more powerful than the Runway Act series and open-source, capable of synthesizing infinite-length videos while achieving up to 6X acceleration in inference speed. Paper: arxiv.org/abs/2512.16900 Code: github.com/Francis-Rings/…