search

Zheng-Chong / CatVTON

CatVTON is a simple and efficient virtual try-on diffusion model with 1) Lightweight Network (899.06M parameters totally), 2) Parameter-Efficient Training (49.57M parameters trainable) and 3) Simplified Inference (< 8G VRAM for 1024X768 resolution).
Other
792 stars 93 forks source link

We couldn't connect to..... #59

Open gregcont opened 1 week ago

gregcont commented 1 week ago

Screenshot 2024-09-23 015121

We couldn't connect to 'https://huggingface.co' to load this model, couldn't find it in the cached files and it looks like F:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\models\CatVTON\stable-diffusion-inpainting is not the path to a directory containing a scheduler_config.json file. Checkout your internet connection or see how to run the library in offline mode at 'https://huggingface.co/docs/diffusers/installation#offline-mode'.

Zheng-Chong commented 1 week ago

This is caused by the delete of repo 'runaway/stable-diffusion-inpainting" in huggingface by RunawayML. You can set "sd15_inpaint_path": "booksforcharlie/stable-diffusion-inpainting“ in your ComfyUI to download from other repo. Or download the new ComfyUI-CatVTON.zip from https://github.com/Zheng-Chong/CatVTON/releases/tag/ComfyUI to replace the old one.

gregcont commented 1 week ago

Do I change it in Extra_model_Paths.yml?

Zheng-Chong commented 1 week ago

In the ComfyUI App. image

gregcont commented 1 week ago

image

Yeah But Manager won't let me install missing nodes.

Zheng-Chong commented 1 week ago

I suggest to reinstall following https://github.com/Zheng-Chong/CatVTON?tab=readme-ov-file#comfyui-workflow.