comfyanonymous
comfyanonymous
Go implement it yourself and you'll see how little people actually care about this model. If you want "an understanding of mathematical concepts" you can just stick an LLM to...
The frontend is the same on local and cloud. If you want things to be as stable as on cloud don't install frontend extensions.
Try this one.
Files can be found here: https://huggingface.co/Comfy-Org/Qwen-Image-Layered_ComfyUI/tree/main/split_files Yes this model is slow.
https://github.com/comfyanonymous/ComfyUI/pull/11304
Wrong text encoder. Correct one can be found here: https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/text_encoders
v0.3.77 is on the stable branch, the ovis model is only implemented in the git/nightly version at the moment.
There's a bug where I enable ram cache on simulated 50GB ram + 24 vram. I run this workflow twice in a row: It unloads the high noise model on...
Seeds are not equivalent between your demo and ComfyUI. If I use the same settings the output image is very close. You have to change the code of your demo...
Yes you can submit a PR.