Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
realcosplay_v10Illust.safetensors
6.46 GB · SafeTensor · bf16 · full
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<realcosplay-ill-xl>
About This Model
STABLE DIFFUSION XL 1.0 · Base Models
Created by
Sennke
on Civitai
Creator notes
RealCosplay is multi-style base models, not limited to realism alone. I don't want to destroy the anime concept of illust or noob,like other Lora or Merge model. So i finetune this model in anime style by default.I'm aimming to use high-quality real photo data to achieve realistic style, and improve anime concept's anatomical\scene composition, through its realistic concept. Recommended settings： - postive prompts for realistic realistic ,cosplay, - negative prompts - （for realistic） illustration,anime,sketch,comic,cartoon,toon,oil painting \(medium\),flat color,outline,3D,2.5D,2D,unreal,unity,blender,anime,smooth skin,semi-anthro,impasto, - （optional）ai-generated,abstract background,worst quality,normal quality,lowres,jpeg artifacts,blurry,fading,mature, - Suggest parameters Euler a cfg : 4~5 Version RealCosplayChenkinV1 2025-12-06 - Recommend using this version – it’s a huge improvement over the old one. - Full finetuning from Chenkin Noob XL V0.1 - The realistic trigger prompt is "realistic" and "cosplay". When generating realistic styles, Please include the recommended negative prompts. Because this is a realistic enhancement base model, not a realistic replacement base model. - Expanded Training Data (now 11,666 images 60% realistic \ 30% anime \ 5% 3d \ 5% other) - Caption with tag+nl (pixai-tagger-v0.9 + Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated Q8）, Manually modified 50% of the captions ,still updating. Version RealCosplay1.2 2025-06-03 - Full finetuning from noob eps 1.1 - The trigger prompt has been changed to "photograph". The previous "realistic" is closer to semi-realistic, which will interfere with the photo-realistic style. - Compared with version 1.0, each has its own advantages. Just use the version you like. - The following rare concept prompt words have been trained Brightness：darkness,dark,dim,bright,overexposure Background：blurry background,depth of field,bokeh,faded background,detailed background,fog Composition：fisheye,partially underground shot,partially underwater shot,high angle,low angle, Screen elements：motion blur,motion line Character age：#*,woman,mature female,age difference, Character feature：wet hair,wet skin,mermaid,muscular male,fat male,tail under clothes, Other：cloud,riding,machine,entry plug,stasis tank,·········· Version RealCosplay1.0 2025-05-09 - Full finetuning from Illustrious - Expanded Training Data (now 6,300+ images) - Greater realistic style, anime styles,compositions, poses, ages, and some rare concept The following rare concept prompt words have been trained Brightness：darkness,dark,dim,bright,overexposure Background：blurry background,depth of field,bokeh,faded background,detailed background,fog Composition：fisheye,partially underground shot,partially underwater shot,high angle,low angle, Screen elements：motion blur,motion line Character age：#*,woman,mature female,age difference, Character feature：wet hair,wet skin,mermaid,muscular male,fat male,tail under clothes, Other：cloud,riding,machine,entry plug,stasis tank,·········· NoobReal Version 3.0 2025-03-07 Feature - Full finetuning from Epsilon-pred 1.1-Version - Improved Dataset Tagging Structure tip: You can still use noobai prompt habits, various style words, artist words, and even mix with realistic styles - Expanded Training Data (now 4,500+ images) - Greater Diversity in compositions, art styles, poses, and character ages - V3.0: Fine-tuned the Cyberfix restoration model to minimize its impact on art style and composition. (During long-term testing, I noticed Cyberfix over-suppressed rare concepts, making it hard to generate dynamic poses or bold compositions. This update aims to fix that) - if you prefer V2.1's style and stable, there is no need to upgrade. The stability of v3.0 is slightly reduced. - 基于Epsilon-pred 1.1-Version进行训练 - 重新调整了训练集标签结构 - 训练集张数4500张 - 更多样的构图、画风、姿势、年龄 - V3.0重新微调了Cyberfix修复模型，极大减少Cyberfix对模型画风、构图的影响。你如果喜欢V2.1的稳定性，依然可以使用V2.1来出图，可以算作2个版本。（我在长期使用后发现Cyberfix会对个别稀有概念降权严重，导致难以生成夸张的身体姿势，整体构图都趋近保守，所以我进行了微调来缓解该问题） NoobReal v2.1 Feature - Mainly trained prompt words（Triggers） - realistic：daily life photos - reversal film：film style - cosplay：more fancy outfits - illustration：My favorite anime mixed styles ( Not necessary for anime style.Mainly enhanced the diversity of character movements. ) - scenery: Enhance scene space logic (Not necessary, I use this word to prevent contamination of anime styles) - depth_of_field: can add to negative words increase background clarity - blurry - simple - Recommended negative words for realistic - blur,film grain,noise,sketch,comic,cartoon,toon,oil painting \(medium\),flat color,outline,3D,2.5D,2D,unreal,unity,blender,anime,smooth skin, - Re-adjusted about 3699 images for - Realistic 60% (95% real photos, 5% AI photos。I don’t like the exaggerated body shape of other nsfw Ai realistic models. so I mostly use real-life photos for training.) - illustration 35% - 3DCG 5% - Tag+NLP mixed captions - better generalizationtrained - better age range - better eye quality - more better realistic background - Hires.fix still recommended. ADetailer are not necessary in v2.1. - Used a self-made version of Cyberfix model to repair the limbs (the original Cyberfix will cause changes in painting style and loss of generalization) - The limbs are not significantly improved compared to 1.0, but 2.1 can generate a wider variety of body movements. - full finetuning from NoobAI-XL v1.0 v1.0 Feature - trained on 3000 images and Tag+NLP mixed caption - better realistic background,The composition will be some different from noobai1.0 - Used CyberFix to fix NoobAI-v1.0's anatomy - New training method - Fixed the noise problem in v0.3 - Hires.fix and ADetailer are no longer required, although still recommended - Supports higher resolutions with less crashing, such as 1024x1536 - Trigger prompt - realistic：daily life photos - cosplay：more fancy outfits - Negative pro
Trigger words
realistic
7,781 downloads · 782 likes on Civitai
SHA256
ED22D03F823E86B0054E18F6F5BB4025DCE095CFC120E8CDFD1E12C041E0FB71
ModelTrends.ai Model ID
#13288
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
DPM++ 2M
Steps
32
Guidance
4.5
Seed
1585574483
Size
832x1216
Prompt
realistic,solo,looking at viewer,holding,glasses,indoors,water,book,no humans,animal,cat,towel,holding book,partially submerged,open book,tiles,reading,animal focus,bathing,bath,animalization,bathtub,tile wall,towel on head,clothed animal,A white cat wears glasses and a pink towel,reading a green book while relaxing in a bath.,
Negative prompt
nsfw,ai-generated,blur,blurry,abstract,old,lossy-lossless,worst aesthetic,low quality,worst quality,bad quality,normal quality,lowres,scan artifacts,jpeg,artifacts,signature,username,text,logo,bad anatomy, extra limbs,extra digit,extra legs,extra legs and arms,disfigured,missing arms,too many fingers,fused fingers,missing fingers,large eyes, illustration,anime,sketch,comic,cartoon,toon,oil painting \(medium\),flat color,outline,3D,2.5D,2D,unreal,unity,blender,anime,smooth skin,semi-anthro,impasto, simple background,faded background,blurry background,depth of field,
Settings
Sampler
DPM++ 2M
Steps
32
Guidance
4.5
Seed
83328163
Size
832x1216
Prompt
(realistic,cosplay:1.1),black background,detailed background,beautiful detailed,high contrast,hazy light,magic element, portrait, 1girl,musou isshin (genshin impact),flowing hair,bangs,long purple hair,eyeshadow,hair accessory,ribbons,dynamic action,looking at viewer, purple kimono,flying flowers around,long sleeves, human scabbard,thunder katana between breasts,electricity, dramatic pose,masterpiece,very awa,highres,best quality,
Negative prompt
ai-generated,old,low quality,worst quality,bad quality,normal quality,lowres,scan artifacts,jpeg,artifacts,signature,username,text,logo,bad anatomy, illustration,anime,sketch,comic,cartoon,toon,oil painting \(medium\),flat color,outline,3D,2.5D,2D,unreal,unity,blender,anime,smooth skin,semi-anthro,impasto, faded background,
Settings
Sampler
DPM++ 2M
Steps
32
Guidance
4.5
Seed
1136952168
Size
832x1216
Prompt
An exquisite digital rendering in anime style features a charming girl with turquoise hair styled in elegant braids,wearing a flowing white kimono embellished with delicate cherry blossom patterns and a pink ribbon tied in her hair. Her eyes are large and luminous,with a gradient of dreamy colors,and her playful grin invites you to share in her joy. Against a pure white background,she stands to the side,turning to face the viewer with curiosity., masterpiece,best quality,(hazy light:1.1),depth of field,bright,
Negative prompt
nsfw,worst quality,bad quality,lowres,jpeg,artifacts,signature,username,text,logo,bad anatomy, extra limbs,extra digit,extra legs,extra legs and arms,disfigured,missing arms,too many fingers,fused fingers,missing fingers,
Settings
Sampler
DPM++ 2M
Steps
20
Guidance
4.5
Seed
2886119050
Size
832x1216
Prompt
direct flash,realistic,cosplay,masterpiece,best quality,highres,detailed skin, 1boy,cigarette,male focus,jewelry,earrings,black hair,solo,shirt,holding cigarette,holding,scar,cross earrings,blue eyes,blood,cross,short hair,looking at viewer,scar on face,smoking,black shirt,collared shirt,one eye closed,upper body,smoke,blood on face,black eyes,getou suguru,ear piercing,single earring,hand up,
Negative prompt
ai-generated,blur,blurry,abstract,old,lossy-lossless,worst aesthetic,low quality,worst quality,bad quality,normal quality,lowres,scan artifacts,jpeg,artifacts,signature,username,text,logo, illustration,anime,sketch,comic,cartoon,toon,oil painting \(medium\),flat color,outline,3D,2.5D,2D,unreal,unity,blender,anime,smooth skin,semi-anthro,impasto,smooth skin,
Settings
Sampler
DPM++ 2M
Steps
32
Guidance
4
Seed
3232784146
Size
832x1216
Prompt
realistic,cosplay,entry plug,riding,souryuu asuka langley,1girl,solo,long hair,breasts,looking at viewer,open mouth,blue eyes,sitting,medium breasts,teeth,sky,orange hair,floating hair,bodysuit,science fiction,controller,pilot suit,plugsuit,red bodysuit,interface headset,cockpit,joystick,front view,A fiery-haired girl in a vibrant red suit clutches a massive weapon. Her outfit,sleek and form-fitting,accentuates her person. The suit's design is futuristic,with glowing details and a number "02" displayed. The background is a cosmic expanse,hinting at a grand,otherworldly battle. The detailed and dynamic,capturing the intensity of the moment.,
Negative prompt
ai-generated,old,low quality,worst quality,bad quality,normal quality,lowres,scan artifacts,jpeg,artifacts,signature,username,text,logo,bad anatomy, illustration,anime,sketch,comic,cartoon,toon,oil painting \(medium\),flat color,outline,3D,2.5D,2D,unreal,unity,blender,anime,smooth skin,semi-anthro,impasto, faded background,
Settings
Sampler
DPM++ 2M
Steps
28
Guidance
5
Seed
1653183298
Size
832x1216
Prompt
1girl, xinzoruo,chibi,kitchen,2b \(nier:automata\),solo,blindfold,apron,slashing,nervous,serious,holding weapon,holding sword,katana,cooking,sweating,carrot is being cut,cutting board, fire on background,explosion, masterpiece,best quality,very aesthetic,absurdres,
Negative prompt
nsfw,worst quality,bad quality,lowres,jpeg,artifacts,signature,username,text,logo,bad anatomy, extra limbs,extra digit,extra legs,extra legs and arms,disfigured,missing arms,too many fingers,fused fingers,missing fingers,
Settings
Sampler
DPM++ 2M SDE Karras
Steps
50
Guidance
5.5
Size
1664x2432
Prompt
1girl, (realistic:1.2), realistic proportions, realistic face, piper wheel, A close-up photograph of a girl with sitting on a concrete ledge in a modern city at sunset, with a subtle smirk. green eyes, blonde hair, goggles around neck, solo, goggles, mask around neck, long hair, hair bun, crop top, hair ornament, short, (thick thighs:0.5), midriff, shorts, chaps, vinyl detached sleeves, sleepy, half lidded eyes, best quality, absurdres, masterpiece, blurry background, looking at viewer,
Negative prompt
AI-generated, worst quality, 2D, 3D, painting, digital art, sketchy, abstract, bad teeth, illustration, sloppy, too-many fingers, bony, bad hands, bad proportions, cheap clothes, costume, cosplay, wide shoulders, wide chest, muscular, skinny,
Settings
Sampler
DPM++ 2M
Steps
32
Guidance
4.5
Seed
220164437
Size
832x1216
Prompt
realistic,1girl,younger,wet hair,solo,long gold hair,looking at viewer,closed mouth,bare shoulders,brown eyes,lips,nose,pool,A wet-haired woman gazes intensely,her dark locks clinging to her face and shoulders. Her expression is serious,lips slightly parted,conveying a sense of contemplation or perhaps longing,emphasizing her features and the texture of her damp hair.,
Negative prompt
nsfw,ai-generated,blur,blurry,abstract,old,lossy-lossless,worst aesthetic,low quality,worst quality,bad quality,normal quality,lowres,scan artifacts,jpeg,artifacts,signature,username,text,logo,bad anatomy, extra limbs,extra digit,extra legs,extra legs and arms,disfigured,missing arms,too many fingers,fused fingers,missing fingers, illustration,anime,sketch,comic,cartoon,toon,oil painting \(medium\),flat color,outline,3D,2.5D,2D,unreal,unity,blender,anime,smooth skin,semi-anthro,impasto, simple background,faded background,blurry background,depth of field,
AI Models for Image, Video & Text Generation
realcosplay ill 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