ComfyUI
ComfyUI copied to clipboard
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Hi, comfyui is awesome!! I'm having a problem where any time the VAE recognizes a face, it gets distorted. I can build a simple workflow (loadvae, vaedecode, vaeencode, previewimage) with...
  Even change the bg-color in the palette, the black in the canvas is not changed.
I was running some training in the background but the `system_stats` endpoint doesn't seem to pick up on the other process' VRAM usage
Reroute node doesnt work on primitive nodes

Can anyone add the ability to use the new enhanced inpainting method to ComfyUI which is discussed here https://github.com/Mikubill/sd-webui-controlnet/discussions/1464
@comfyanonymous I don't expect you to merge this in, but I just thought I'd ask your opinion 😊
Hey, I've spent quite some time looking at your example on the basic usage of this, I've tried loading in the CLIP model alone, and just using one in a...
### Description It would be convenient if it was possible to choose a color in the node for RGB and RGBA. I'll try to describe how I see it. For...
OS: Ubuntu 22.04 GPU: AMD RX 6800 XT Python version 3.10.6 CLI args: python main.py --listen --use-split-cross-attention UI loads fine and is able to see my checkpoints, lora's, vae's. etc....