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.

Downloads last month: 21

Safetensors

Model size

0.3B params

Tensor type

F32

Inference Providers NEW

Video-to-Video

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for cicada-ai/Chanjing-Avatar-V2V-5B

Base model

Wan-AI/Wan2.2-TI2V-5B

Finetuned

(81)

this model