It all started with a single image generated using the Pony model.
(See this tutorial for more details.)
Illustrious v1 – Created using just one base image.
Pony v1 – Built from the original image plus 24 images generated with Illustrious v1. Trained over 10 epochs with 16 repeats per image.
Illustrious v2 – Same setup as Pony v1, but using the Illustrious model as the base.
Pony v2 – Same as Pony v1, but trained over 50 epochs with only 1 repeat per image.
For generation tips, trigger words, and version-specific notes, please refer to the documentation provided with each version.
I hope you enjoy using this LoRA!
Feel free to rate it, leave comments, and share your creations — your feedback is always appreciated.
Thank you!
How to generate correct image with WAI-NSFW-illustrious-SDXL generation
Use at 0.8 strenght.
Use a least "Srdtmq, hair over eyes" as trigger words
Recommended settings for text-to-image:
Sampler: Euler A (Karras)
Sampling steps: 20
CFG scale: 6
Then, send your result to image-to-image with:
Sampling steps: 30
CFG scale: 6
Denoising strength: up to 0.75 (lower values for a closer match to the original image)
Extras: ADetailer (for face, not for eyes cause she has hair over eyes).
Go ahead and upload yours!
Your query returned no results – please try removing some filters or trying a different term.