Jogg-Avatar V2V 5B

Jogg-Avatar V2V 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.

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

Jogg-Avatar-Wan2.2-5B/
|-- 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: -

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/Jogg-Avatar-V2V

Base model

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

Finetuned

(76)

this model