ComfyUI wrapper nodes for WanVideo

WORK IN PROGRESS

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

Text encoders to ComfyUI/models/text_encoders

Transformer to ComfyUI/models/diffusion_models

Vae to ComfyUI/models/vae

You can also use the native ComfyUI text encoding and clip vision loader with the wrapper instead of the original models:

TeaCache (temporary WIP naive version, waiting on the official one) I2V:

Context window test:

1025 frames using window size of 81 frames, with 16 overlap. With the 1.3B T2V model this used under 5GB VRAM and took 10 minutes to gen on a 5090:

This very first test was 512x512x81

~16GB used with 20/40 blocks offloaded

Vid2vid example:

with 14B T2V model:

with 1.3B T2V model