You can check out the other models and images I've generated here!
https://civarchive.com/user/nununu568
https://civarchive.com/user/nununu568
I mixed in a few photorealistic models.
🦌🦌🦌🦌🦌🦌🦌🦌🦌🦌🦌🦌🦌🦌🦌🦌🦌🦌🦌🦌🦌🦌🦌🦌🦌🦌🦌
V2.0~ int8 models can be loaded using Comfyui's native loader! You're running the latest version of Comfyui, right!?
for ~v1.1 int8 model
ComfyUI-INT8-Fast
https://github.com/BobJohnson24/ComfyUI-INT8-Fast
About the 4step Model
alibaba-pai/Z-Image-Fun-Lora-Distill
https://huggingface.co/alibaba-pai/Z-Image-Fun-Lora-Distill
I tried merging the 4steplora for ZIB.
I know that ZIT weights aren’t used, but I felt it might be effective when actually applied, so I gave it a try.
RTX 3060 with 12GB of VRAM, it can generate a 1024×1024 image in under 10 seconds.
0.5Mpixels
1Mpixels
Lora might not be working right.
sample
w 4step LORA
w/o 4step LORA
Description
FAQ
Comments (3)
我有个疑问，如果4步生图，我给它8步或者更多，能不能提升一点生图质量。还是会过拟合？
I have a question, if I give it 8 steps or more to generate a 4-step image, can it improve the quality of the image a bit. Will it still overfit?