Instructions to use GINJILISM/wan22-runpod-comfyui-cache with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Wan2.2
How to use GINJILISM/wan22-runpod-comfyui-cache with Wan2.2:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Wan2.2 RunPod worker-comfyui Model Cache
This repo is a RunPod runpod/worker-comfyui compatible Model Cache wrapper for Wan2.2 T2V 14B.
It mirrors selected files from:
Comfy-Org/Wan_2.2_ComfyUI_RepackagedComfy-Org/Wan_2.1_ComfyUI_repackagedfor theumt5text encoder
into the directory layout expected by worker-comfyui:
models/
vae/
clip/
unet/
loras/
RunPod usage
Set Endpoint → Model Cache Repository to this repo ID.
The workflow JSON should use bare filenames, not absolute paths:
wan_2.1_vae.safetensors
umt5_xxl_fp8_e4m3fn_scaled.safetensors
wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors
wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors
wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors
wan2.2_t2v_lightx2v_4steps_lora_v1.1_low_noise.safetensors
- Downloads last month
- -