Sign In

HorizonXL anime

93
857
9
Updated: Sep 26, 2023
base modelanimegirls
Verified:
SafeTensor
Type
Checkpoint Trained
Stats
857
0
Reviews
Published
Sep 26, 2023
Base Model
SDXL 1.0
Hash
AutoV2
CC22438DC0
kitarz's Avatar
kitarz

recommend to use natural language and more sytle prompts

推荐使用自然语言和足够多的质量/画风prompts

Recommend:

step:35,DPM++ 3M SDE Karras,

recommand prompts in show image.

Here are a few examples:

example 1
{ "prompt": "breathtaking,{prompt} . gorgeous,key visual, vibrant, studio anime,award-winning, professional, highly detailed,high budget, cinemascope",

"negative_prompt": "noisy, blurry, grainy,text, graphite, abstract, glitch, deformed, mutated, ugly, disfigured,black and white, low contrast"},

example 2

{"prompt": "Fairy tale {prompt} . Magical, fantastical, enchanting, storybook style, highly detailed,gorgeous, vibrant, award-winning, professional, ",

"negative_prompt": "realistic, modern, ordinary, mundane"}

Train base Kohaku-XL , this model after MBW to remove most of the contamination,while preserving the generalization ability of the base model.

Image will be closer to kohaku-XL,only retaining the style of my interference,it's normal, I do it on purpose!

基于 kohaku-XL模型训练,训练后与底模进行了MBW去除了大部分的污染,保留了底模的泛化性。出图会比较接近kohaku-XL,只保留了我干涉的画风,很正常,我故意的。