Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
obsessionIllustrious_vPredV20.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
<obsession3il-xl>
About This Model
STABLE DIFFUSION XL 1.0 · Base Models
Created by
rqdwdw
on Civitai
by rqdwdw - Obsession (Illustrious-XL) -- Like other Illustrious style models, it istens well to otaku anime artist names for style, otherwise the style might look plain, so don't forget to add your favorite artists to your prompts like this: people, characters, copyright, style, general tags, rating, masterpiece, best quality, good quality, newest Negative Prompts lowres, worst quality, bad quality, bad anatomy, sketch, jpeg artifacts, signature, watermark, old, oldest
Creator notes
v-pred_v2.0 Carefully Curated Danbooru Dataset (up to September 2025) Base Model: - When necessary, please use Rescale CFG with values up to around 0.7 (especially for NSFW content). Quality Tags: very aesthetic > masterpiece > best quality > good quality > normal quality > worst quality If you feel like it, you can support me on . Thank you. Online Generator: v-pred_v1.1 Dataset:50k AI-generated images from Aibooru and Pixiv + 10k images from Danbooru Prompts people, characters, copyright, style, general tags, rating, masterpiece, best quality, good quality, newest Negative Prompts lowres, worst quality, bad quality, bad anatomy, sketch, jpeg artifacts, signature, watermark, old, oldest Base model: + v-pred_v1.0 Base model: Use v-prediction and Zero Terminal SNR. For information on v-prediction and how to use it in ComfyUI, refer to the by L_A_X. As of November 20, checkpoints supporting v-prediction are not available for use in stable-diffusion-webui. Outside of ComfyUI, you can use the (likely requiring a .yaml file for each checkpoint) or and . Additionally, make sure to select "Zero Terminal SNR" under Settings → Sampler parameters → Noise schedule for sampling. v3.1 Base model: v-pred_v0.1 Base model: v3.0 Base model: v2.1 Base model:(noobaiXLNAIXL_epsilonPred075 x 0.7 + noobaiXLNAIXL_epsilonPred05Version x 0.3) v2.0 Base model: v1.0 Base model: After training, this model merged into the U-net. (0,0.3,0.25,0.2,0.15,0.1,0.15,0.2,0.25,0.3,0.3,0,0.05,0.15,0.25,0.3,0.25,0.15,0.05,0) License
16,327 downloads · 1,299 likes on Civitai
SHA256
5D1C3F154D2F86348FE5FD35BD818D23BFBE3F7D77F834526E5924EA08292426
ModelTrends.ai Model ID
#14664
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
Steps
32
Guidance
4
Seed
1367968000
Size
640x1536
Clip skip
2
Prompt
1girl, solo, halloween, knight, jack-o lantern, halloween costume, safe,short hair,brown hair,jewelry,heart,earrings,choker,blunt bangs,black choker,bob cut,mole on breast, smile, cute, medium breasts, masterpiece, best quality, newest, higres, absurdes, usnr, dovahkiin armor, brown gauntlets, horned helmet, brown knee boots, holding axe, axe, <lora:e5cb501a-3c66-425e-aa92-d1fcbd5a4f84:0.4>, <lora:bb939a58-e240-43d2-95a2-500ab5c8a52b:0.5>, <lora:c68a4cbe-1364-43b2-85d0-47157eb691e8:0.5>, <lora:f6784438-d152-4f5f-acca-c217db0a0f5a:0.7>, <lora:9f3c6491-ee81-4ff1-858e-9441e8cec2a3:0.7>
Negative prompt
worst quality, bad quality, low quality, jpeg artifacts, old, oldest, signature, simple background
Settings
Sampler
Euler a
Steps
20
Guidance
7
Seed
1689341190
Size
768x1280
Clip skip
2
Prompt
(masterpiece:3), best quality, good quality, newest, highres, absurdres, best quality, very awa, absurdres,(extreme aesthetic:1.3), (very aesthetic:1.2), (dynamic composition:1.3), (dynamic angle:1.3),(volumetric lighting:1.3), (ambient occlusion:1.2), (depth of field:1.3), (light particles:1.2), (glowing:1.3), (pastel shimmer:1.3), (sparkles:1.2),(cute colors:1.3), pastel colors, (4k,8k,Ultra HD), best quality, ultra-detailed, very aesthetic, depth of field, best lighting, detailed illustration, detailed background, cinematic, beautiful face, ambient occlusion, raytracing, soft lighting, 8K, illustrating, CG, detailed background, (dynamic pose:1.2), (dynamic angle:1.1), divine mystic aesthetic, minimalist background, double exposure, dynamic pose, bloom, depth of field,perspective, volumetric lighting, shade,shadow,detailed background, (chromatic aberration:1.4), wlop, epic, sketc ,1girl,solo,short hair,hair ornament,dress,sitting,pink hair,flower,outdoors,sky,barefoot,cloud,white dress,from side,bare legs,profile,cover,building,scenery,sunset,city,cityscape,Light,shadow,Sunset,best quality,depth of field,cinematic lighting,light particles,lens flare,impactful picture,offcial art,movie perspective,high quality,extremely detailed,High Detail,(Tyndall Effect 1.4),cover art,extreme aesthetic,masterpiece,best quality,good quality,newest,Visual impact,32K UHD,sharp focus, (qiandaiyiyu:0.85), (soleil \(soleilmtfbwy03\):0.6), (godiva ghoul:0.65), (anniechromes:0.5), silhouette, solo, BREAK (rella:1.2), (redum4:1.2) (au \(d elete\):1.2) (dino \(dinoartforame\):1.1), <lora:holographiccolor:0.3> qxys <lora:illustrious_best_quality_v1:0.5> <lora:ponyv6_noobV1_2_adamW:0.3> <lora:Illustrious_V2:0.7> <lora:Ethereal_Aesthetic:0.3>
Negative prompt
ng_deepnegative_v1_75t,(badhandv4:1.2),EasyNegative,(worst quality:2),
Settings
Sampler
RES Multistep
Steps
20
Guidance
5.5
Seed
3080917523
Size
2080x3040
Prompt
s3lfxp, very aesthetic, <lora:s3lfxp_noobv_b01:0.7>, ceiling monster, 1girl, 1other, hornet \(hollow knight\), red dress, from behind, overlooking, atmospheric perspective, holding weapon, white weapon, wide shot, dark, yellow water, sickly, maggots, white worms, too many maggots, uboa, size difference, from below,
Negative prompt
worst quality, too many hornets, hollow knight \(character\),
Settings
Sampler
Euler
Steps
40
Guidance
5
Seed
1973308678
Size
768x1152
Prompt
(masterpiece:3), best quality, good quality, newest, highres, absurdres, best quality, very awa, absurdres,(extreme aesthetic:1.3), (very aesthetic:1.2), (dynamic composition:1.3), (dynamic angle:1.3),(volumetric lighting:1.3), (ambient occlusion:1.2), (depth of field:1.3), (light particles:1.2), (glowing:1.3), (pastel shimmer:1.3), (sparkles:1.2),(cute colors:1.3), pastel colors, (4k,8k,Ultra HD), best quality, ultra-detailed, very aesthetic, depth of field, best lighting, detailed illustration, detailed background, cinematic, beautiful face, ambient occlusion, raytracing, soft lighting, 8K, illustrating, CG, detailed background, (dynamic pose:1.2), (dynamic angle:1.1), divine mystic aesthetic, minimalist background, double exposure, dynamic pose, bloom, depth of field,perspective, volumetric lighting, shade,shadow,detailed background, (chromatic aberration:1.4), wlop, epic, sketc masterpiece, beautiful, high quality, masterpiece, beautiful, high quality, very awa, skeleton, golden crown, long black cloak, flowing cloak, pristine bones, close up:2.1, hallow eyes, at an angle, ecliptical midnight, night, darkness, heavy shadow, deep shadows, dark shadows, digital art, (big breasts:1.3) surreal, dynamic composition, (depth of field:1.5), (4k,8k,Ultra HD), (masterpiece :1.5), (best quality :1.5), (detailed:1.5), (dynamic pose:1.4), (abstract background:1.4), (intricate details:1), digital art, surreal, dynamic composition, (harada takehito:1.2), (kotteri,masha,himukai yuuji:1.2), <lora:holographiccolor:0.3> qxys <lora:illustrious_best_quality_v1:0.5> <lora:ponyv6_noobV1_2_adamW:0.3> <lora:Illustrious_V2:0.7> <lora:Ethereal_Aesthetic:0.3>
Negative prompt
(NSFW:2.5), worst quality, bad quality, low quality, jpeg artifacts, old, oldest, signature, sketch, bad quality,worst quality,worst detail, censor, bad anatomy, error, bad anatomy, bad hands, watermark, ugly, distorted, signature
Settings
Sampler
LMS
Steps
44
Guidance
5
Seed
1675309791
Size
1664x2432
Clip skip
2
Prompt
cutesy-co, aliasing, jaggy lines, BREAK, absurdres, dark red background, decorative background, froggy chair, smiling chair, happy chair, smile, green chair, serval \(kemono friends\), 1girl, sitting, shinji in a chair \(meme\), spotted clothes, spotted pants, cinematic lighting, face in hands, elbows on knees, (from above:0.5), <lora:CutesyCo_illu_v2_g2_d3216_goodoladafactor:1>
Negative prompt
feet on chair, nsfw, nude, young, loli, multiple views, lowres, bad anatomy,
Settings
Sampler
Euler a
Steps
30
Guidance
5
Seed
3733647203
Size
768x1280
Clip skip
2
Prompt
very aesthetic, 1girl, eri \(blue archive\), misyune, sushispin, dotori \(seulseul\), ningen mame, witch hat, smile, glowing, halo, holding staff, magic, (((hat tug))),looking at viewer, open mouth, bloom, floating clothes, v-shaped eyebrows, floating hair, depth of field, shirabi, modare, freng, masterpiece, best quality, newest
Negative prompt
worst quality, bad quality, low quality, jpeg artifacts, old, oldest, signature, simple background
Settings
Sampler
Euler a
Steps
20
Guidance
7
Seed
2999894345
Size
768x1152
Prompt
masterpiece, best quality, good quality, newest, highres, absurdres,masterpiece, best quality, very awa, absurdres,(extreme aesthetic:1.3), (very aesthetic:1.2), (dynamic composition:1.3), (dynamic angle:1.3),(volumetric lighting:1.3), (ambient occlusion:1.2), (depth of field:1.3), (light particles:1.2), (glowing:1.3), (pastel shimmer:1.3), (sparkles:1.2),(cute colors:1.3), pastel colors, (4k,8k,Ultra HD), masterpiece, best quality, ultra-detailed, very aesthetic, depth of field, best lighting, detailed illustration, detailed background, cinematic, beautiful face, ambient occlusion, raytracing, soft lighting, 8K, illustrating, CG, detailed background, 1girl, (dynamic pose:1.2), (dynamic angle:1.1), divine mystic aesthetic, minimalist background, (futuristic regal attire:1.3), haute couture sci-fi fashion, (veil:1.2), sheer metallic fabric veil, face partially obscured by golden tassels and ornaments, delicate veil of shimmering tassels, glittering gemstones, demon horns, horns, red hair BREAK (elaborate jeweled headdress:1.3), intricate golden filigree, pearls, chains, symbolic charms, pearlescent necklace, flowing textiles, soft translucency, (qiandaiyiyu:0.85), (soleil \(soleilmtfbwy03\):0.6), (godiva ghoul:0.65), (anniechromes:0.5), silhouette, solo, double exposure, dynamic pose, bloom, depth of field,perspective, volumetric lighting, shade,(shadow),detailed background, (chromatic aberration:1.4) BREAK (rella:1.2), (redum4:1.2) (au \(d elete\):1.2) (dino \(dinoartforame\):1.1), wlop, epic,ma1ma1helmes_b_illu,sketc <lora:holographiccolor:0.3> qxys <lora:illustrious_best_quality_v1:0.5> <lora:ponyv6_noobV1_2_adamW:0.3> <lora:Illustrious_V2:0.7> <lora:Ethereal_Aesthetic:0.3>
Negative prompt
worst quality, bad quality, low quality, jpeg artifacts, old, oldest, signature, sketch, bad quality,worst quality,worst detail, censor, bad anatomy, error, bad anatomy, bad hands, watermark, ugly, distorted, signature
Settings
Sampler
Euler a
Steps
28
Guidance
5
Seed
2207478949
Size
1344x640
Clip skip
2
Prompt
very aesthetic, 1girl, castorice \(honkai: star rail\), koujuian, konya_karasue, jima, reoen, upper body, asymmetrical gloves, black tiara, blue butterfly, bright pupils, dress bow, elbow gloves, long hair, looking at viewer, lying, on back, purple butterfly, purple eyes, purple flower, purple gloves, solo, tiara, uneven gloves, white bow, white dress, white pupils, white thighhighs, wlop, dino \(dinoartforame\), depth of field, bloom, masterpiece, best quality
Negative prompt
worst quality, bad quality, low quality, jpeg artifacts, old, oldest, signature, sketch
AI Models for Image, Video & Text Generation
obsession3il 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