🎞 LoRA is trained purely on anime screencaps
🗝 Activation tags are in the right panel
📝 Note: Very limited dataset, so her outfit isn't exactly stable.
📸 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 (2)
dude... thats the 24th, did you automate or something holy f
Naah 😅 I already had the screencaps, just needed to bring them up to standard from sd1.5. So a bit of retaggining and thankfully most of them have the same serafuku. Sooo batch edits do speed up things a lot.