THIS MODEL HAS BEEN ARCHIVED AS IT NO LONGER CONFORMS TO MY CURRENT QUALITY STANDARDS!

Old Description:

• Current version: 2.0

• Recommended weight: 0.8-1.0 (the more LoRa's are chained together the lower this needs to be)

• Recommended VAE: SDXL 0.9

• Recommended model: SDXL 1.0

• Recommended inference settings: See example images

I recommend using the official SDXL 1.0 model that has the SDXL 0.9 VAE already integrated, which you can find here.

Trigger words

• mn artstyle

Further usage notes

Note that the model currently tends to generate young looking characters. Unfortunately my dataset was quite limited (mostly Makoto Shinkai movies) to preserve quality, so it does not have many images of actual adult looking woman, due to the nature of the current anime industry of having mostly young looking characters.

Changelog

v2.0

• Moderately improved quality

• Closer to Makoto Shinkai's style

• Massively improved compatibility when used in conjunction with other LoRa's

• Increased file size

v1.0

• Initial release

Description

Anime artstyle LoHa for SDXL 1.0 trained (not merged) by me (AI_Characters). Credit is not mandatory but I would still appreciate credit when posting images using this LoHa on social media! Feel free to @ my Twitter and/or Instagram accounts too (@ai_characters)! I would love to know when it is used!

If you want to support what I am doing, donations to my Ko-Fi would be greatly appreciated! Those will go towards funding the renting of GPUs for further experimentation and model making.

Feel free to also try out my RVC2 AI voice models which you can find here!

Stats

Dataset:

• 133 images (screencaps)

Training:

• rented RTX A4090 on Vast.ai

• Training time: ~1h 30min

• Example training configuration (v3)