USED:
https://github.com/lllyasviel/Fooocus
https://github.com/anapnoe/stable-diffusion-webui-ux
Wow New XL Model!!!
You have to try this for yourself!
Super fast builds at "normal" XL resolutions with much better quality than the base SDXL 1.0!
Suggested settings for best results
Sampler:
DPM++SDE,
DPM++ SDE Karras,
DPM++ 3M SDE exponential
Steps: 3 - 5
CFG: 1 - 2.25
You can run this model on Automatic1111 like a normal XL model, however not all samplers work... it's the best output performance, willing to wait a little longer. The LCM and Euler A sampler produce almost identical results, which can be used at low passes, but are really lacking in detail compared to the other options.
for your direct contributions to this model, and a lot of thanks and love ❤️❤️ to the patient model testing team, who I am constantly bombarding with new LoRA and internal builds...
You will be notified of any future versions you publish. I also need your help with the comments. Please post your pictures and your honest comments below. I'll use your feedback and results to help guide future revisions!