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】AnyLoraCleanLinearMix_ClearVAE and LoRA to generate a yukata image of Yami from ToLove-Ru

スポンサーリンク

This time I tried to generate a yukata image of Yami from ToLove-Ru using AnyLoraCleanLinearMix_ClearVAE and LoRA!
This article is just a reminder.

contents

スポンサーリンク

abstract

Model, LoRA and prompts used in generating ToLove-Ru's Yami's yukata image on google colab and diffusers

1.requirement

Google Colab
Diffusers transformers==4.26.0
model : AnyLoraCleanLinearMix_ClearVAE
LoRA: yami 3 in one (To Love Ru Darkness)
LoRA:Detail Tweaker LoRA

2.result

positive prompt

(masterpiece:1.6, best quality), (finely detailed beautiful eyes: 1.2), phyami, yaminor, 1girl, solo, blonde hair, long hair, red eyes, very long hair, BREAK yukata

negative prompt

(worst quality, low quality:1.4), monochrome, zombie, (interlocked fingers:1.2), bad-hands-5, mutated hands, liquid fingers, extra fingers, missing fingers

seed=6690356537517

seed=12760174729134

seed=34377442784336

スポンサーリンク

3.refarence

civitai.com