ComfyUI_ExtraModels
ComfyUI_ExtraModels copied to clipboard
city96
Support for miscellaneous image models. Currently supports: DiT, PixArt, HunYuanDiT, MiaoBi, and a few VAEs.
PsuedoTerminal is doing some really interesting work with expanding the model depth from 28 -> 42 and finetuning on new data, for example: https://huggingface.co/ptx0/pixart-900m-1024-ft I tried hacking the code to...
ampler: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! File "E:\AI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all)...
Hi, I'm trying to run Hunyuan Dit version 1.1 on Comfy UI. I installed ComfyUI_ExtraModels" and followed the instructions on the main page. Used the sample workflow on your page...
``` 11:47:06.416 [Warning] ComfyUI-0 on port 7821 stderr: Traceback (most recent call last): 11:47:06.417 [Warning] ComfyUI-0 on port 7821 stderr: File "C:\Users\*****\Downloads\StableSwarmUI\dlbackend\comfy\ComfyUI\nodes.py", line 1890, in load_custom_node 11:47:06.417 [Warning] ComfyUI-0 on...
For some reason, Pixart Sigma images are coming out as some sort of incomprehensible mess. I followed the directions as best I could and used the sample workflow, but this...
There is a new model with a 16ch vae and 3B parameters : https://github.com/THUDM/CogView3?tab=readme-ov-file. Could you possibly support it ?
It would be nice to have Lycoris support for Pixart-Sigma models.
Hey there, I found the Force/Set CLIP Device node to be causing extreme slowdown in my workflows, when set to 'cpu'. In particular this line pops up in the console:...
New Sana version 4.8b 😀 https://huggingface.co/Efficient-Large-Model/SANA1.5_4.8B_1024px
