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】アニメ画像が生成できるcaulkinumV2forAnimeStyleを試してみた

スポンサーリンク

spy x familyのLoRAを試している中でcaulkinumV2forAnimeStyleなるモデルがあることを知ったので
早速試してみようかと思います

目次

スポンサーリンク

この記事でわかること

google colabとdfiffusersでcaulkinumV2forAnimeStyleを使うとどのような画像が生成できるか

1.実行環境

Google Colab
Diffusers transformers==4.26.0
model : caulkinumV2forAnimeStyle

2.生成結果

positive プロンプト

1girl, parted lips, blush, makeup, light smile, school uniform, classroom, light rays, glow, thighs, collarbone, narrow waist, (masterpiece), wallpaper

negative プロンプト

EasyNegative, sketch, duplicate, ugly, huge eyes, text, logo, monochrome, worst face, (bad and mutated hands:1.3), (worst quality:2.0), (low quality:2.0), (blurry:2.0), horror, geometry, bad_prompt, (bad hands), (missing fingers), multiple limbs, bad anatomy, (interlocked fingers:1.2), Ugly Fingers, (extra digit and hands and fingers and legs and arms:1.4), crown braid, ((2girl)), (deformed fingers:1.2), (long fingers:1.2),succubus wings,horn,succubus horn,succubus hairstyle, (bad-artist-anime), bad-artist, bad hand, too many hair, cat ears, animal ears



スポンサーリンク

3.参考

civitai.com

【Stable Diffusion】AnyLoraCleanLinearMix_ClearVAEとLoRAでToLoveるの結城美柑の水着画像を生成してみた

スポンサーリンク

今回はAnyLoraCleanLinearMix_ClearVAEとLoRAでToLoveるの結城美柑の水着画像生成をやってみました
この記事は備忘録になります

目次

スポンサーリンク

この記事でわかること

google colabとdiffusers上でToLoveるの結城美柑の水着画像を生成する際に使用したモデルとLoRAとプロンプト

1.実行環境

Google Colab
Diffusers transformers==4.26.0
model : AnyLoraCleanLinearMix_ClearVAE
LoRA: Mikan Yuuki (結城 美柑) - To Love Ru (とらぶる)
LoRA:Detail Tweaker LoRA

2.生成結果

positive プロンプト

mikanyuuki,mikan yuuki, solo, 1girl, (brown eyes:1.7), brown hair, hair ornament, hair scrunchie, long hair, pink scrunchie, scrunchie, (flat chest:1.2), BREAK bikini ,BREAK looking at viewer, BREAK outdoors, sea, ocean, (masterpiece:1.2), best quality, high resolution, unity 8k wallpaper, (illustration:0.8), (beautiful detailed eyes:1.6), extremely detailed face, perfect lighting, extremely detailed CG, (perfect hands, perfect anatomy),

negative プロンプト

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

seed=9037876841933

seed=38821291357789

seed=39565620982703

スポンサーリンク

3.参考

civitai.com

【Stable Diffusion】AnyLoraCleanLinearMix_ClearVAE and LoRA to generate an image of Ichika Nakano of the Quintessential Quintuplets

スポンサーリンク

This time I tried to generate an image of Ichika Nakano of Tthe Quintessential Quintuplets with AnyLoraCleanLinearMix_ClearVAE and LoRA!
This article will be a memorandum.

contents

スポンサーリンク

abstract

Model, LoRA and prompts used in generating the image of Ichika Nakano of the Quintessential Quintuplets on google colab and diffusers.

1.requirement

Google Colab
Diffusers transformers==4.26.0
model : AnyLoraCleanLinearMix_ClearVAE
LoRA: Nakano Ichika 中野一花 / 5-Toubun no Hanayome
LoRA:Detail Tweaker LoRA

2.result

positive prompt

aaichika, short hair, white shirt, collared shirt, green skirt, chool uniform, cowboy shot, 1girl, parted lips, blush, makeup, light smile, classroom, light rays, glow, thighs, collarbone, narrow waist, (masterpiece), best quality, highres, wallpaper

negative prompt

easynegative, myself-badhand-v5, (worst quality, low quality:1.4), monochrome, zombie, (interlocked fingers:1.2), mutated hands, liquid fingers

seed=16095190851334

seed=30959827664308

seed=80644606276328

スポンサーリンク

3.refarence

civitai.com

【Stable Diffusion】AnyLoraCleanLinearMix_ClearVAEとLoRAでその着せ替え人形は恋をするの喜多川海夢の水着画像を生成してみた

スポンサーリンク

今回はAnyLoraCleanLinearMix_ClearVAEとLoRAでその着せ替え人形は恋をするの喜多川海夢の水着画像生成をやってみました
この記事は備忘録になります

目次

スポンサーリンク

この記事でわかること

google colabとdiffusers上でその着せ替え人形は恋をするの喜多川海夢の水着画像を生成する際に使用したモデルとLoRAとプロンプト

1.実行環境

Google Colab
Diffusers transformers==4.26.0
model : AnyLoraCleanLinearMix_ClearVAE
LoRA: Kitagawa Marin/喜多川海夢/きたがわ まりん/My Dress-Up Darling/戀上換裝娃娃/その着せ替え人形は恋をする(着せ恋)
LoRA:Detail Tweaker LoRA

2.生成結果

positive プロンプト

Marin Kitagawa, 1girl, solo, long hair, blonde hair, red eyes, piercing, earrings, ear piercing, stud earrings, bikini, parted lips, blush, makeup, light smile, BREAK bikini, sea, ocean, light rays, glow, thighs, collarbone, narrow waist, (masterpiece), wallpaper, highres, best quality, 8k, very clear,

negative プロンプト

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

seed=51697465376509

seed=62002013766385

seed=70822632461790

スポンサーリンク

3.参考

civitai.com

【Stable Diffusion】AnyLoraCleanLinearMix_ClearVAE and LoRA generated a swimsuit image of Chizuru Mizuhara from Rent-A-Girlfriend

スポンサーリンク

We have previously generated an image of Chizuru Mizuhara from Rent-A-Girlfriend.
This time, we tried to generate a swimsuit version of Chizuru Mizuhara's image

contents

スポンサーリンク

abstract

Model and LoRA and prompts used in generating the swimsuit image of Chizuru Mizuhara of Rent-A-Girlfriend on google colab and diffusers

1.requirement

Google Colab
Diffusers transformers==4.26.0
model : AnyLoraCleanLinearMix_ClearVAE
LoRA: Mizuhara Chizuru 彼女、お借りします Ichinose Chizuru 水原千鶴 Kanojo, Okarishimasu
LoRA:Detail Tweaker LoRA

2.result

positive prompt

upper body, brown hair, long hair, bangs, brown eyes, bikini, cleavage, blue wrist scrunchie, small breasts, breasts focus, Exquisite visuals, high-definition, masterpiece, best quality,

negative prompt

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

seed=13387618146384

seed=22304407645350

seed=49787879877079

スポンサーリンク

3.refarence

civitai.com

【Stable Diffusion】I tried creationmix v1 which can generate animated images

スポンサーリンク

I've been experimenting with LoRA related to animation, and I found out that there is a model called AingDiffusion.
I'm going to give it a try right away!

contents

スポンサーリンク

abstract

What kind of images can be generated using creationmix with google colab and dfiffusers

1.requirement

Google Colab
Diffusers transformers==4.26.0
model : creationmix v1

2.result

positive prompt

1girl, parted lips, blush, makeup, light smile, school uniform, classroom, light rays, glow, thighs, collarbone, narrow waist, (masterpiece), wallpaper

negative prompt

EasyNegative, sketch, duplicate, ugly, huge eyes, text, logo, monochrome, worst face, (bad and mutated hands:1.3), (worst quality:2.0), (low quality:2.0), (blurry:2.0), horror, geometry, bad_prompt, (bad hands), (missing fingers), multiple limbs, bad anatomy, (interlocked fingers:1.2), Ugly Fingers, (extra digit and hands and fingers and legs and arms:1.4), crown braid, ((2girl)), (deformed fingers:1.2), (long fingers:1.2),succubus wings,horn,succubus horn,succubus hairstyle, (bad-artist-anime), bad-artist, bad hand, too many hair, cat ears, animal ears



スポンサーリンク

3.refarence

https://civitai.com/models/68075/creationmix-v1-standard-illustration-style-checkpoint

【Stable Diffusion】狼と香辛料のホロの着物画像を作ってみた

スポンサーリンク

以前に狼と香辛料のホロの画像生成を行いました
今回は着物バージョンの画像生成をやってみました
この記事は備忘録です

目次

スポンサーリンク

この記事でわかること

google colabとdiffusers上で狼と香辛料のホロの着物画像を生成する際に使用したモデルとLoRAとプロンプト

1.実行環境

Google Colab
Diffusers transformers==4.26.0
model : YesMix LoRA: Holo + Outfits & Style | Spice & Wolf LoRA:Detail Tweaker LoRA

2.生成結果

positive プロンプト

holo, small breasts, BREAK closed mouth, masterpiece, best quality, absurdres, 1girl, looking at viewer, standing, room, neck pouch, slender, BREAK BREAK furisode, kimono, upper body, leaning forward, grin, arms behind back, medieval, room

negative プロンプト

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

seed=1013045553866

seed=5128849971665

seed=6675514453766

スポンサーリンク

3.参考

civitai.com