Comfy-Org / Comfy-Org/ComfyUI

Please support Wan2.1 - MoCha ~

Open
#10,500 1 comment 3 reactions 0 assignees View on GitHub
Feature
Dominant language
Python
Stars
133k
Forks
15.7k
Avg merge
1d 7h
Merged PRs (30d)
158

Description

### Feature Idea

[ Wan 2.1 - Video Character Replacement ]

MoCha: Based on Wan 2.1, it's a simpler and easier-to-use video character replacement model. It's more user-friendly than Wan 2.2-Animate. Simply mask the character in the first frame to replace the video character, preserving the original frame's dynamic lighting and shadows.

https://github.com/Orange-3DV-Team/MoCha
https://orange-3dv-team.github.io/MoCha/

Model Download:
https://huggingface.co/Orange-3DV-Team/MoCha

Model quantized by Kijai:
https://huggingface.co/Kijai/WanVideo_comfy_fp8_scaled/tree/main/MoCha

![Image](https://github.com/user-attachments/assets/6295c774-67c2-4f07-b448-d0b2bf7c8cde)

Since it's also the base model for Wan2.1, I believe you can easily support it. Thank you~

### Existing Solutions

Thank you~

### Other

_No response_

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.