UPDATE: removed noise offset, slightly less training, better for combining with multiple other LoRAs

Finally, after much trial and error, I believe this LoRA came out really well. But you be the judge: let me know what you think and post your own generated images. See features, how to use and examples below.

New features:

• easy to make good gens on anime models like AOM2 (click "view more" in the gallery to see non cherry-picked batches)

• compatible with other LoRAs, to fit your style, pose and even use it as an outfit/cosplay for other characters, since you can change hair color

• works with various models, including anime, 2.5D and realistic (some realistic models may require more tweaking the prompt, weight and CFG to get the best results; see my examples)

How to use:

• Works with weight 0.6-1.0 and CFG 5-8 , depending on the model (e.g. higher weight and CFG for realistic models)

• Main trigger word: shimakaze

• The main trigger word will generally provide the outfit, but these trigger words can be used to emphasize the character/outfit: blonde hair, striped thighhighs, microskirt, elbow gloves, sailor collar, anchor hair ornament, highleg panties, black panties

• Other keywords associated with the character and context: robot, turret, lifebuoy

Batch grid (same prompts, different seeds, various models)

AOM2

Counterfeit-v2.5