This is a general purpose model, that can generate people, cars, spaceships, aliens etc...
Recommended image sizes for SDXL
1024 x 1024
1152 x 896
896 x 1152
1216 x 832
832 x 1216
1344 x 768
768 x 1344
1536 x 640
640 x 1536
Notes:
Training base was 500 images
9,000 steps
10 epochs
Recommended clip skip of 1
Available now on www.thinkdiffusion.com
Description
FAQ
Comments (1)
No one seems to have commented on this model yet, so I will.... I found it from ThinkDiffusion, and so far it is the best model to work with my custom SDXL character LoRAs. I've tried using them on Base SDXL and Juggernaut, but they never look right. But they look great when I use them with Oasis. Thank you for making this; it is becoming my go-to as I delve deeper into the XL side of Stable Diffusion!