🎞 LoRA is trained purely on anime screencaps
🗝 Activation tags are in the right panel
📝 Note:
When generating yellow pinafore dress, instead of brown sash, sometimes brown belt can appear
📸 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)
How did you train your LoRA? How many images and which tool did you use?
All the info is on Arc En Ciel discord.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.



