Disclaimer(s)

If you generate with my content, and you'd like to share it, please consider using the "Add Post" button at the bottom of the gallery.

I want to be clear about something. My LoRAs may contain content from publicly available mods. If you are bothered by something you made being associated with AI.. quite frankly that's too bad. You don't own my dataset nor my time.

Prompt Usage

Here is what I think you should know about each LoRA. I didn't include quality tags, expressions, poses, and the other stuff. Reference sample images for those.

• Recommended LoRA Strength is about the 0.8 range.

• Trying to remove headwear? Use missing headwear. A lot of outfits with headwear that cover the head include images with it taken off. Could be useful.

• If you're going for anime styles like my samples, put 3d, realistic, game screenshot in negatives.

• If you use the hair styles, colors or eyes in the section above, you might generate my player character.

Training Parameters

All my outfits contain 50 images with varied poses, angles and frames. They are mostly locally trained, but some are trained with AI Toolkit. The Illustrious versions trained on site might be slightly baked.

Load my safetensor into LoRA Metadata Viewer if you're curious about any settings.. if you can see them.