Introduction
A LORA model of Owari from Azur Lane.
Usage
Trigger tag:
owari \(azur lane\)Key Feature: white hair, black horns, hair over one eye, dark-skinned female, braid, mature female
Generating Settings
Base Model: Arbitrary anime model
Sampler: DPM++2M Karras, DPM++3M Karras and other DPM samplers are recommended.
Eta noise delta: 31337 or 0
Upscale Method: HiresFix+4xAnimeSharp
Max Resolution without Upscaling: 1024x1024
VAE: kl-f8-anime2 is recommended.
LORA Weights: 0.6~0.8 are recommended.
Cautions
For Anime model, pls disable 'face restoration' during generating.
Make sure set this option in 'Stable Diffusion' settings to 'CPU' to successfully regenerate the preview images with the same seed.

The training resolution of this model is 1024x1024, so generating resolution must not exceed this range. Try to use 'hires fix' to prevent this problem and help to generate higher-resolution images.
Description
FAQ
Comments (5)
NIKKE的黑白兔有计划做做优化版吗🥺🥺
有,最近在实验新方法,可以在保证质量的情况下减小文件大小
@zakp 那个。。。白兔的白色网袜,只靠你的Lora很难生成。黑兔的Lora对背景影响比较大,生成的背景和灯光色调会比较固定,大概跟你说一下现有的问题🥺
@GoldenMiocola 黑兔当时用的数据量比较少,因为那个角色当时刚出没多久,现在图应该变多了
@zakp 嗯嗯 总之希望能有兼容性比较好的版本,人物动作灵活一点的,衣着还原准确一些的💕💕













