🎞 LoRA is trained purely on anime screencaps
🗝 Activation tags are in the right panel
Check about version for differences over previous version.
📸 Always use ADetailer to get detailed eyes
🛠 Technical notes:
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
Difference over v0.1:
added additional images from the anime to the training dataset
fixed some dataset tags
stabilized her hair with "hair rings"
added 'hair down' images
added 'twin braids' images
Note: There is no version 1.0, I'm updating this one straight to 2.0