ComfyUI_ExtraModels
ComfyUI_ExtraModels copied to clipboard
city96
Support for miscellaneous image models. Currently supports: DiT, PixArt, HunYuanDiT, MiaoBi, and a few VAEs.
https://github.com/Efficient-Large-Model/ComfyUI_ExtraModels/issues/2 I already posted in here but I'm not sure which of the repo is right so yea > I successfully trained a model with Sana (full fine-tune safetensor from...
NVIDIA have published the [new 2k model](https://huggingface.co/Efficient-Large-Model/Sana_1600M_2Kpx_BF16/tree/main/checkpoints), but no select in Sana Checkpoint Loader nor Sana Resolution Select to use it.
GemmaLoader The checkpoint you are trying to load has model type `gemma2` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or...
I've made a fresh install on a Ubuntu machine and here are some errors in the README: 1.  2. Only the VAE on the right works for me: 
 I tried downloading without comfy Ui, means, I downloaded through hugging face manually. Even though it is not recognizing existing download. It is downloading again. Don't know how to...
I have 3 gpus, a 3090, 3080, and p40. the force/set clip device shows only "cpu" and "cuda:0". when I set the comfy device to cuda:0 it shows cuda:1 instead....
use this brach: https://github.com/Efficient-Large-Model/ComfyUI_ExtraModels/ where to put gemma loader's model , huggingface cache and in model not work, I:\cache\huggingface\hub\models--unsloth--gemma-2-2b-it-bnb-4bit F:\ComfyUI\ComfyUI\models\text_encoders\unsloth\gemma-2-2b-it-bnb-4bit Prompt executed in 80.75 seconds got prompt Unused kwargs: ['_load_in_4bit',...
Strange behaviour if batch size >1. It is the same with gemma on cpu or on cuda...  
hi I appreciate your work but it doesn't work for me. Some dependencies are missing and I don't know what version is appropriate for them I tried everything and followed...
