MergeStove2.5D / README.md
LieDeath's picture
minor fix
c1f6998
|
raw
history blame
3.63 kB
metadata
license: cc-by-nc-4.0
language:
  - en
library_name: diffusers
pipeline_tag: text-to-image
tags:
  - art

MergeStove2.5D

A merge stable diffusion model specialize in anime, which improves anatomy of anime characters, especially with eyes and hands, without losing anime objects.
much better for working at 0.9K-1.2K resoultion, or use Hires.fix instead.
Provide in mk1 and mk2 version. Personally mk1 works better, but mk2 give out more vivid pictures

No commercial usage!

Preview

12848-2569952539-miku, ruby eyes, face to viewer, solo, medium breasts, soft light, outdoors, garden, seaside, beauty.png mk1 (after hi-res fix) miku, ruby eyes, face to viewer, solo, medium breasts, soft light, outdoors, garden, seaside, beauty 12908-2604523401-miku, crystal eyes, upper body, face to viewer, solo, medium breasts, soft light, garden, seaside, ocean, bikini.png mk1 miku, crystal eyes, upper body, face to viewer, solo, medium breasts, soft light, garden, seaside, ocean, bikini 12867-1973802650-miku, crystal eyes, upper body, face to viewer, solo, medium breasts, soft light, outdoors, garden, seaside, beauty, blue white.png mk1 miku, crystal eyes, upper body, face to viewer, solo, medium breasts, soft light, outdoors, garden, seaside, beauty, blue white dress 12947-375827774-miku, crystal eyes, upper body, face to viewer, solo, before bookshelf, book in hands.png mk2 miku, crystal eyes, upper body, face to viewer, solo, before bookshelf, book in hands 12948-2412520204-miku, crystal eyes, upper body, face to viewer, solo, before bookshelf, book in hands.png mk2 miku, crystal eyes, upper body, face to viewer, solo, before bookshelf, book in hands 12949-2375419362-miku, crystal eyes, upper body, face to viewer, solo, before bookshelf, book in hands.png mk2 miku, crystal eyes, upper body, face to viewer, solo, before bookshelf, book in hands

Usage

Use as normal stable diffusion model package, no external yaml config is needed.

Tags

Positives as you like, maybe less quality words works better.
Negatives better to use the basic prompts, or just replace as bad_prompt embedding.

Bias

include nsfw contents due to its original models!
DO NOT USE your generated pictures for Pirate human artists or any Internet Violence! Such as on Bilibili or Youtube
Sometimes long necks appear. Still hazy a bit. Under some theme will produce wrong skin gloss. Sometimes overfitting.

Formula

Round1 animefull-latest(NovelAI)+64in1(Private, from a Chinese AI community NovelAI 中文频道) sum rate0.4
Round2 ()+AbyssOrangemix2_nsfw(WarriorMama777) sum rate0.2
After baked in vae-ft-mse-840000-ema-pruned(StabilityAI) VAE, pruned ema, compressed to FP16, get MergeStove2.5D_mk1.

Round3 MergeStove2.5D_mk1+Anmokomergetest1(Private, from a Chinese AI community NovelAI 中文频道) sum rate0.4
After baked in vae-ft-mse-840000-ema-pruned(StabilityAI) VAE, pruned ema, compressed to FP16, get MergeStove2.5D_mk2.