🎞 LoRA is trained purely on anime screencaps
🗝 Activation tags are in the right panel
📝 Note: The dataset consists purely of images from 100 year quest, as it had the most detailed eyes out of all series.
📸 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 ;)