Acly
Acly
The Python downloads don't go through QNetworkAccessManager, they use `uv`
It usually means the server crashed without explanation. Most likely cause is running out of RAM. Flux requires quite a lot, depending on how much you have it might just...
GPU is fine, I meant system RAM. Although the Nunchaku models don't use all that much of that either. Are you able to run Flux without Nunchaku? (eg [this model](https://huggingface.co/Clybius/FLUX.1-Krea-dev-scaled-fp8/tree/main))...
What are the inputs and outputs of a custom Control Layer? (ie in a ComfyUI workflow)
The highlight not being at the right position could be improved. But I think to fix it properly means trying to rewrite the buttons displayed on top of thumbnails using...
Hi! From what it looks like your Blender plugin works in a similar way to [custom graphs](https://docs.interstice.cloud/custom-graph/#creating-workflows) in Krita. How are they implemented? The Krita plugin uses "Parameter" nodes as...
Yea I think this will work for very basic scenario. I just wanted to point out that it's probably a bad approach for everything that is a little more complex...
ComfyUI keeps websocket connections in a `dict` which maps client-id -> socket, so there can only be one connection per ID. Which makes sense to allow reconnects. > Actually one...
Fixed in [v1.43.0](https://github.com/Acly/krita-ai-diffusion/releases/tag/v1.43.0)
This usually means your GPU can't handle the model or image size. Try smaller model or canvas resolution (don't know what your GPU is)