LoRA is generated entirely from anime images.
Should work well with any model.
Check samples for prompts :)
Leave a like, comment, review but first of all, ENJOY ;)
If you wish to support me in my work,
you can do that here: Ko-Fi.com/LittleJelly
Description
FAQ
Comments (7)
Thanks! She's perfect.
Don't forget to leave a review as you requested her ;)
great work, like LORA just purely made from anime... impressive result.
Could you please make "Aoba Suzukaze" from "New game!" in this style too ? I'd really like to see your result :)
Sorry, I haven't seen the anime and in general I don't really do requests.
Just scraping screenshots from anime takes a lot of time. :/
The images for me are slightly blurry and are kinda unsaturated. Is there a way to enhance the quality of the image?
-> txt2img, hires. fix (4x-AnimeSharp upscaler), sampling 30, denoising 0.6-0.7
-> send it to -> img2img (0.1 denoising)
-> send it to extras (4x-AnimeSharp upscaler)
@LittleJelly Oh boy! That worked pretty well. Thank you very much!