🎞 LoRA is trained purely on anime screencaps
🗝 Activation tags are in the right panel
📸 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)
I recommend for character stability: Haruhime,long hair,blonde hair,blunt bangs,green eyes,animal ears,fox tail,large breasts,DanMachi,without pupils,yellow tail
It is also better to use ADetailer for the eyes.
The moment you use Haruhime and DanMachi tag, you are no longer using data from LoRA but whatever is cooked inside a checkpoint. So, not recommended.