🎞 LoRA is trained purely on anime screencaps
🗝 Activation tags are in the right panel
📝 Note: University hair jumps from left to right, can't get it more stable due to lack of HQ images in the dataset
📸 Always use ADetailer to get detailed eyes
🛠 Technical notes:
LoRA shoud be compatible with Illu models & NoobAI. (Not tested.)
LoRA is compatible with various styles - Lower the weight & remove "anime screencap" from the prompt, if you are getting too strong anime style
Hi. res fix used on all sample images:
Upscaler: R-ESRGAN 4x+ Anime6B
Steps: 10-15
Denoising: 0.3
📬Leave a like, comment, review but first of all, ENJOY ;)
Description
FAQ
Comments (3)
Jelly, thank you for all these amazing loras you share. The quality is simply awesome.
Also, these Fate characters are incredible. Saber one looks so cool too!
Thank you very much again, Jelly!
Maybe I am just dumb, but I feel like you might want to include "anime screencap" in the trigger words section. I was like how I can not generate the image that looks similar to yours then I noticed that I did not include "anime screencap". Once I included it, problem solved.
I don't include it because it's a style tag. Im keeping the trigger words solely to chara specific tags :)