Chanjing-Avatar V2V 5B

Chanjing-Avatar V2V 5B is an audio-driven video-to-video avatar model based on Wan2.2-TI2V-5B. It preserves the source video's body, camera, and background motion while regenerating the face region to follow a driving audio track.

Training and inference code is available at chanjing-ai/Chanjing-Avatar-V2V-5B.

Chanjing-Avatar Model Family

• Chanjing-Avatar 14B: 720p image-to-video generation from a reference image and driving audio.
• Chanjing-Avatar V2V 5B: video-to-video generation that preserves source motion and regenerates the speaking face.
• Chanjing-Avatar V2V 1.3B: a lighter video-to-video model for audio-driven face animation.

Use these weights with the Chanjing-Avatar V2V 5B code repository. The model directory must contain:

Chanjing-Avatar-V2V-5B/
|-- config.json
`-- diffusion_pytorch_model.safetensors

The Wan2.2 base model and facebook/wav2vec2-base-960h are required separately. Review their licenses and terms before use. Users are responsible for obtaining consent for source videos and voices and for clearly disclosing synthetic media.