Resources

Hi~Regarding the 20260412 model, is it possible to provide an official FP8 model-comfyui, or an official Lora-comfyui?

#19 opened 16 days ago by

RedHn

Is there a recommended sampler/scheduler for the distill models in comfyui?

#18 opened 20 days ago by

Cldoerick

model is too big ,we need new lora-0412 of high&low，thx！

#17 opened 24 days ago by

RedHn

Question

#16 opened about 1 month ago by

YarvixPA

Is there a workflow for nodes that load multiple LoRa modules? Thank you.

#15 opened 4 months ago by

wzgrx

How this model is trained

#14 opened 4 months ago by

pxyy

Is there any way to run T2V with 4 step inference?

#13 opened 5 months ago by

neuralityAI

T2V Version?

#12 opened 6 months ago by

spooknik

Will there be FP4 quantization?

#10 opened 6 months ago by

hlufeng

Unet Missing ..

#9 opened 6 months ago by

hanswurstwerner

1030 FP8 E4M3 version is bad result in comfyui

👍 3

#7 opened 7 months ago by

t8star

Is there any chance that you will do something similar for T2V models?

#5 opened 7 months ago by

Ruzarh

Should Wan2.2-Distill-Models used with Distill Loras?

👍 2

#4 opened 7 months ago by

Cjayk

add pipeline tag for better discoverability :)

🔥 1

#3 opened 7 months ago by

linoyts

ComfyUI will still cast all layers to fp8

#2 opened 7 months ago by

silveroxides

Error with quantized models using the "Load Diffusion Model" node in ComfyUI

#1 opened 7 months ago by

xuanwoa