ComfyUI
ComfyUI copied to clipboard
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
### Your question Hey guys, I installed ComfyUI along with Flux, the installation went fine, but when I tried to generate the first image using Flux, I noticed it was...
### Your question Hi all, After install some new custom nodes, I now get these errors at ComfyUI startup. I searched for this kind of message already but I have...
Micro-optimization for Chroma. Replaces ops with `addcmul` or `Tensor.addcmul_` where appropriate. Intended to try to mimic some of the performance gains that torch.compile gets through pointwise fusion -- this isn't...
### Your question Hello, great work and thanx a lot for that. Searge LLM runes without problem in my portable version etc. But when I use the ComfyUI Setup File...
When using ComfyUI with Radeon + ROCm + WSL (and possibly other use cases) VAE encode/decode typically always results in OOM and reverts to the tiled version. There is already...
### Feature Idea I want to modify this file: **extra_config.py,** then it will be works better. I already tested on my windows, it worked. ComfyUI_windows_portable\ComfyUI\utils\extra_config.py ### Existing Solutions ``` import...
### Custom Node Testing - [x] I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.comfy.org/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help) ### Your question Hello!...
The `get_gpu_names` function should have a docstring explaining its purpose, arguments, and return value. This makes the code easier to understand and maintain.
### Your question Florence2ModelLoader only DaViT is supported for now ### Logs ```powershell ``` ### Other _No response_
### Your question Hi, I´m getting random OOM and retries of allocation errors. I´m using a Jetson AGX Orin 64G (Ubuntu 22, python 3.10 using conda, Cuda 12.4), it has...