This is a Furry/Yiff LORA trained to emulate the style of the artist "Jishinu" with about 4K Steps.
It's really good at the style itself and can even replicate certain characters pretty well, thanks to the dataset.
Multi character scenes also generate nicely.
I recommend using at 0.5 strength.
I hope you will enjoy this model!
Description
Re-Trained Model with newer and more streamlined dataset.
Creates better, more consistent output.
Recommend using at 0.41 strength and with DPM++2M SDE Karras sampler.
FAQ
Comments (1)
I've been a long time fan of Jishinu's artworks, and this LoRA is just cherry on top. The recent v2 update is very cool and works flawlessly with different models, I tested it with YiffyMix, EasyFluff and BB95 Furry Mix. I understand that I could have gotten even better results with a Highres fix but unfortunately I don't have enough VRAM for that. Nevertheless, the style is quite consistent and the outlines are smooth and sharp. Thank you very much for your work, @FuOx <3 For everyone else, I recommend adding "oil painting" to the negative prompt for better results. And my personal preference is to use YiffyMix model with this LoRA and "(by backlash91)" added to the prompt for extra sharp images.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.