T

snomiao 9ac4d6fcd6 chore(publish): update GitHub Actions workflow for node publishing

- Add permissions for issue writing
- Set condition to run job only for 'kijai' repository owner
- Update action version from 'main' to 'v1' for stability and consistency

2025-02-26 10:10:41 +00:00

.github

chore(publish): update GitHub Actions workflow for node publishing

2025-02-26 10:10:41 +00:00

configs

init

2025-02-25 20:03:08 +02:00

example_workflows

vid2vid, cfg scheduling

2025-02-26 01:13:13 +02:00

wanvideo

fp8 option for T5

2025-02-26 11:35:52 +02:00

__init__.py

init

2025-02-25 20:03:08 +02:00

.gitattributes

Initial commit

2025-02-25 15:23:26 +02:00

.gitignore

init

2025-02-25 20:03:08 +02:00

fp8_optimization.py

init

2025-02-25 20:03:08 +02:00

nodes.py

Update nodes.py

2025-02-26 11:59:05 +02:00

pyproject.toml

some kind of preview

2025-02-25 23:25:06 +02:00

readme.md

some kind of preview

2025-02-25 23:25:06 +02:00

requirements.txt

cleanup

2025-02-25 22:13:48 +02:00

utils.py

init

2025-02-25 20:03:08 +02:00

readme.md

ComfyUI wrapper nodes for WanVideo

WORK IN PROGRESS

Installation

Clone this repo into custom_nodes folder.
Install dependencies: pip install -r requirements.txt or if you use the portable install, run this in ComfyUI_windows_portable -folder:

python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\ComfyUI-WanVideoWrapper\requirements.txt

Models

https://huggingface.co/Kijai/WanVideo_comfy/tree/main

Text encoders to ComfyUI/models/text_encoders

Transformer to ComfyUI/models/diffusion_models

Vae to ComfyUI/models/vae

Right now I have only ran the I2V model succesfully.

This test was 512x512x81

~16GB used with 20/40 blocks offloaded

https://github.com/user-attachments/assets/fa6d0a4f-4a4d-4de5-84a4-877cc37b715f