Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
illusionbreed_v30.safetensors
6.46 GB · SafeTensor · fp16 · pruned
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<illusionbreed3-xl>
About This Model
STABLE DIFFUSION XL 1.0 · Base Models
Created by
JujoHotaru
on Civitai
by JujoHotaru - Recommended output settings CFG Scale : 4-5 Sampler : Eular A Sampling steps : 20 - 40 Resolution : mainly tested on 768x768, 768x1152, 832x1216, 800x1200 and 1024x768
Creator notes
(日本語説明は後半にあります) v7.0 Update : Made detailed adjustments and modifications at each block(IN, OUT, MID) and text encoder to improve background quality, composition, and overall finish. About this model "IllusionBreed" is an Illustrious-based SDXL checkpoint, pursuing "kawaii", cuteness. There are 2 variations for v7.0 : - Basic 2D painting style - "Slender" : 2D painting and more slender body style - To download each types, switch version tabs ↑ above. I feel that model merging is similar to the breeding of flowers (to improve their appearance), so named "Breed". These models have special features : - Include many originally trained data to adjust painting style (saturation, tone), eye shape, and quality (finely detailed pupils, finely detailed outlines, fine painting, reducing grain noise etc). - Detailed backgrounds. - Powerful prompting based by Illustrious (and NoobXL). More various other LoRA's and Checkpoints are released on my or . Please check it out. Recommended output settings - CFG Scale : 4-7 (recommended : 5) - Sampler : Eular A - Sampling steps : 20 - 60 (recommended : 40) - Resolution : mainly tested on 768x768, 768x1152, 832x1216, 800x1200 and 1024x768 - Using A-Detailer (for face etc.) is highly recommended. (inpaint denoising strength : 0.3 for face, 0.5 for breasts, etc.) - HiRes Fix : use SwinIR_4x, R-ESRGAN 4x+ or 4x-UltraSharp with denoise strength 0.3-0.7. - Quality prompt / Negative prompt : See below. - VAE : embedded. Quality prompts sample This and base checkpoints are derived from Illustrious, so use quality prompts for Illustrious models. masterpiece, best quality, amazing quality, very aesthetic, absurdres, perfect anatomy, perfect symmetrical face, cute face, perfect hands, detailed eyes, detailed hair, slender, (PUT YOUR PROMPTS HERE) To improve background quality, detailed background, photo background, blurry background prompt is recommended. Negative prompts sample lowres, bad quality, worst quality, bad anatomy, sketch, jpeg artifacts, ugly, poorly drawn, blurry, watermark, bad eyes, bright pupils, white pupils, bad hands, bad face, (PUT YOUR NEGATIVE PROMPTS HERE) このデータモデルについて v7.0 アップデート：IN/OUTの各階層ごとに細かく変更・調整を加え、背景品質や構図・仕上がりなどを改善しています。 IllusionBreedは、二次元イラストレーション生成に特化した「Illustrious」派生形モデルで、可愛さを追求しています。 v7.0では、以下2種類のバリエーションが用意されています： - 基本2Dタイプ - Slender : 2Dタイプ、若干頭身が高めのボディースタイル - 各タイプをダウンロードするには、ページ上部のバージョンタブを切り替えてください。 私はモデルのマージはお花の交配（品種改良）と近いものを感じているため、作成したデータモデルの名前には品種改良を意味する「Breed」を付けています。 Breedシリーズの特徴として、作者が独自に学習させた多数のLoRAをマージすることで、画質・色味・陰影や眼の形などを調整したり、輪郭線および眼の質感向上や粒子ノイズ低減、HiRes Fixの高品質化などを図っています。 使い方 - 推奨される出力設定や品質指定プロンプト・ネガティブプロンプトなどは上記を参照してください。 - 背景の描写品質を上げたい場合、背景関連のプロンプトに detailed background, photo background, blurry background を追加することを推奨します。 - サンプラーに「Eular A」系統以外を使うと画質が劣化しやすいので注意してください。 - ネガティブプロンプトは空にせず、低品質系のワードを入れて調整したほうが良い画質が出やすいようです。（高速出力などのため使えない場合は無くても大丈夫です） - A-Detailerの使用を推奨します。顔のリファインのInpaint denoising strengthは0.3、裸体の胸には0.5程度がよいでしょう。 - ネコミミなど動物耳キャラクターを生成する場合、人間耳を出さないようにするも用意しています。 VAEは焼き込み済みですので、別途用意する必要はありません。 他にもさまざまなLoRAやデータモデルを公開していますので、またはをご覧ください。 Merge recipe (for v1.0) - Based on 8 models (all merged with ratio 0.125) : - - - illuminous_v01 - - - - - - Original finetuned data with / outputs - Original trained LoRAs for eye shape/painting/detailing - VAE
2,445 downloads · 273 likes on Civitai
SHA256
F523FED4CF9F94B2F63874184804F9EF8984714B98CA61F3D24F64EDCF3D8CF4
ModelTrends.ai Model ID
#17384
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
Euler a
Steps
40
Guidance
5
Seed
4098778963
Size
768x1152
Prompt
masterpiece, best quality, amazing quality, very aesthetic, absurdres, cute round face, slender, detailed eyes, detailed hair, kawaii, 1girl, solo, (mature:0.5), dynamic angle, (running away from dog:1.3), best shadow, an extremely delicate and beautiful, gleaming skin, cowboy shot, upset, nervous sweating, open mouth, in forest, park, garden, cityscape, standing, dynamic pose, street fasion, casual fashion, harajuku fashion, wearing skirt, pink hair, > < <lora:hotarueye_xl_comic01_v20_ill:1>
Negative prompt
lowres, bad quality, worst quality, bad anatomy, sketch, jpeg artifacts, ugly, poorly drawn, blurry, watermark, bad eyes, bright pupils, white pupils, bad hands, bad face, nipples, nsfw
Settings
Sampler
Euler a
Steps
40
Guidance
5
Seed
3708653690
Size
768x1152
Prompt
masterpiece, best quality, amazing quality, very aesthetic, absurdres, cute round face, slender, detailed eyes, detailed hair, kawaii, 1girl, solo, wearing kimono, smile, open mouth, standing, model pose, cowboy shot, night, starry sky, Night sea Capture the mesmerizing beauty of the ocean, depth of field, ultra detailed background, medium breasts, grey hair, red eyes, long hair <lora:darkness_xl_v20:1.2>
Negative prompt
lowres, bad quality, worst quality, bad anatomy, sketch, jpeg artifacts, ugly, poorly drawn, blurry, watermark, bad eyes, bright pupils, white pupils, bad hands, bad face, nsfw
Settings
Sampler
LCM
Steps
4
Guidance
1
Seed
636800675
Size
896x1152
Clip skip
2
Prompt
1girl, fischl \(genshin impact\), very awa, deffis, green eyes, eyepatch, blonde hair, two side up, long hair, black hair ribbon, black nails, back tattoo, black dress, tailcoat, purple bowtie, bare shoulders, gloves, long sleeves, asymmetrical legwear, single thighhigh, black thighhighs, garter straps, single leg pantyhose, black pantyhose, dynamic angle, simple background, chuunibyou, smile, Purple background, wind, close-up, falling feathers, masterpiece, best quality, highres, absurdres, sensitive <lora:NoobV065sHyperDmd:1> <lora:Fischl_IXL:1>
Negative prompt
worst quality, low quality, lowres, signature, username, logo, bad hands, mutated hands, ambiguous form, muscular,
Settings
Sampler
Euler a
Steps
8
Guidance
1.5
Seed
2907542156
Size
1024x1024
Clip skip
2
Prompt
masterpiece, best quality, amazing quality, 2girls, (poptepipic pose:1.2), (bkub \(style\):1.2), white background, BREAK, amate, red hair, multicolored hair, short hair, multicolored eyes, aqua shirt, striped necktie, white sweater, aqua skirt, grey socks striped red, black boots, BREAK, nyaan, tall female, slender, long hair, hair between eyes, bangs, blunt bangs, deep blue hair, multicolored eyes, dark blue jacket, black ribbon, pleated skirt, school uniform, black socks, white shoes, <lora:Hyper-SDXL-8steps-lora:1> <lora:amate-000008:0.8> <lora:Nyaan:0.8>
Negative prompt
lowres, worst quality, bad quality, signature, watermark, censor, copyright name
Settings
Sampler
LCM
Steps
4
Guidance
1
Seed
3508660305
Size
896x1152
Clip skip
2
Prompt
1girl, fischl \(ein immernachtstraum\) \(genshin impact\), very awa, einfis, official alternate costume, red eyes, white eyepatch, eyepatch, blonde hair, long hair, hair ribbon, tiara, purple dress, bare shoulders, long sleeves, purple sleeves, frills, choker, asymmetrical legwear, single thighhigh, white thighhighs, single leg pantyhose, white pantyhose, high heels, purple footwear, Purple Lightning, falling feathers, standing, dynamic angle, simple background, chuunibyou, smile, Purple background, wind, from front, masterpiece, best quality, newest, highres, absurdres, sensitive <lora:NoobV065sHyperDmd:1> <lora:Fischl_IXL:1>
Negative prompt
worst quality, low quality, lowres, signature, username, logo, bad hands, mutated hands, ambiguous form, muscular,
Settings
Sampler
Euler a
Steps
40
Guidance
5
Seed
4112418960
Size
768x1152
Prompt
masterpiece, best quality, amazing quality, very aesthetic, absurdres, cute round face, slender, ultra detailed eyes, ultra detailed hair, ultra beautiful, 1girl, solo, a cute girl, cute round face, princess, wearing princess costume, princess dress with many frills, tiara on hair, happy smile, closed mouth, from side, standing, cowboy shot, looking at viewer, fantasy world, castle, medium large breasts, pink hair, long hair, messy hair, green eyes, hair between eyes
Negative prompt
lowres, bad quality, worst quality, bad anatomy, sketch, jpeg artifacts, ugly, poorly drawn, blurry, watermark, bad eyes, bright pupils, white pupils, bad hands, bad face
Settings
Sampler
Euler a
Steps
40
Guidance
5
Seed
1432672146
Size
768x1152
Prompt
masterpiece, best quality, amazing quality, very aesthetic, absurdres, cute round face, slender, detailed eyes, detailed hair, kawaii, 1girl, solo, cowboy shot, shooting from front, smile, closed mouth, looking at viewer, medium hair, blonde hair, dark green eyes, white school uniform, medium breasts, school ground, school, yard, buildings, city, grass, extremely detailed background, photoreal background <lora:eyelashext_v10:-1>
Negative prompt
lowres, bad quality, worst quality, bad anatomy, sketch, jpeg artifacts, ugly, poorly drawn, blurry, watermark, bad eyes, bright pupils, white pupils, ugly, bad hands, bad face
Settings
Sampler
Euler a
Steps
40
Guidance
5
Seed
3638808287
Size
768x1152
Prompt
masterpiece, best quality, amazing quality, very aesthetic, absurdres, cute round face, slender, detailed eyes, detailed hair, kawaii, 1girl, solo, (mature:0.5), dynamic angle, (running away from very big dog:1.3), best shadow, an extremely delicate and beautiful, gleaming skin, cowboy shot, upset, nervous sweating, open mouth, in forest, park, garden, cityscape, standing, dynamic pose, street fasion, casual fashion, harajuku fashion, wearing skirt, pink hair, > < <lora:hotarueye_xl_comic01_v20_ill:1>
Negative prompt
lowres, bad quality, worst quality, bad anatomy, sketch, jpeg artifacts, ugly, poorly drawn, blurry, watermark, bad eyes, bright pupils, white pupils, bad hands, bad face, nipples, nsfw
AI Models for Image, Video & Text Generation
illusionbreed3 xl is a base model for the Stable Diffusion XL 1.0 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion XL 1.0 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Browse all models