First time doing a LoRA, I'm amazed by the results :D
Very special thanks to Trauter for teaching me how to do everything! https://civitai.com/user/Trauter
Improved version with edited out watermarks and more focus on fdg in training data, should give better results.
Trained on 832 resolution, higher initial resolution e.g. 768 x 1024 should give better results.
Too lazy to test, I'll just drop 1 image :3
Go ahead and upload yours!
Your query returned no results – please try removing some filters or trying a different term.