HunyuanVideo-Avatar
Tencent Hunyuan portrait video generation — one image + audio into lifelike video
Tencent Hunyuan portrait video generation: one image plus audio produces natural, lifelike video.
AI video generation, digital humans, and video restoration.
Key features
- Audio-driven human animation with emotion-controllable output
- Multi-character dialogue video generation
- Supports photorealistic, cartoon, 3D-rendered, anthropomorphic avatars
- Portrait, upper-body and full-body multi-scale generation
- Runs on single GPU with 10GB VRAM via TeaCache
Good for
- Talking avatar videos for e-commerce and streaming
- Multi-character dialogue scene generation
Stack & tags
Gradioavataraudio-driventalking-heademotion-controlmulti-characteropen-weightsdit
Similar open-source projects
Hyperframes
★ 55,468Write HTML. Render video. Built for agents — HeyGen's open-source video framework
Hypit
★ 18,649Clone any viral video with AI agents — swap the face, the words, the B-roll, ship 100 variants