こすたろーんエンジニアの試行錯誤部屋

作成物の備忘録を書いていきますー

【Stable Diffusion】I used the model BRA V5 for realistic human image generation

スポンサーリンク

So far I have tried to generate images using "BlueberryMix", "BeautyProMix" and "mutsuki_mix".
This time, I will try to generate images using V5 of BRA (Beautiful Realistic Asians), which is good at generating realistic images.
Prompts are the same as those used in BlueberryMix, BeautyProMix and mutsuki_mix
I would be happy to help with model selection and prompting!

contents

abstract

What kind of images can be generated with BRA V5

1.requirement

Google Colab
Diffusers transformers==4.26.0
model : BRA V5
lora : koreanDollLikeness_v20

2.result

positive

masterpiece, ultra high res, 1 girl, (photo realistic:1.2),small_breasts,cleavage,smile,detailed beautiful skin, face focus, (black eyes), cute, young, looking at viewers, (scoop neck tee:2.0), ,collarbone, ((black hair)), windy, soft light, hand between legs, from front

negative

painting,sketches,(worst quality:2),(low quality:2),(normal quality:2),lowers,normal quality,((monochrome)),((grayscale)),skin spots,acnes,skin blemishes,age spot,(outdoor:1.6),nsfw,ugly face,fat,(missing fingers),extra fingers,extra arms,extra legs,open chest,chest pad

seed = 14441039949112

seed = 30012885998884

seed = 36650501792673

refarence:BlueberryMix

refarence:BeautyProMix

refarence:mutsuki_mix

In comparison, BRA V5 looks more mature and gives the impression of a more natural image.

スポンサーリンク

refarence

civitai.com
github.com
note.com