This is my first experiment with fine-tuning stable diffusion. I named it Flexible-Diffusion, since unlike the heavily fine-tuned models out there for specific styles, this one is very broad and can almost be used in place of SD 1.5, seeds usually give similar results, but with better aesthetics, general coherence, and center subject placement.
It can be used with regular 1.5 prompts, AND also works great with Danbooru tags!
Some example comparisons between SD 1.5 and Flexible diffusion:
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.