Model
Trends
.ai
Model
Trends
.ai
les meilleurs modèles d'IA open source
Exécuter en local
illustriousXLv01_stable_dark_v0.3.safetensors
61 MB · SafeTensor
Les téléchargements sont servis par Civitai. Certains créateurs demandent d'abord une connexion à Civitai.
AD
<dark-ill-xl>
À propos de ce modèle
STABLE DIFFUSION XL 1.0 · LoRA
Créé par
reakaakasky
sur Civitai
Dark [IL] by reakaakasky
Notes du créateur
Dark Lower the brightness. And make it more photography-ish. All cover images are directly from a1111, no upscale, no face/hands fixes, even no negative prompt. I trained this LoRA because anime models have a very high bias towards bright images. So even if you prompted something dark, it still not dark enough, most part of the image still very bright. However, I can't find a "dark" LoRA that is for natural dark. Because existing LoRAs are - Either trained on bright images, so you have to use negative strength to go dark, which is doable, but the quality is really bad. - Or focusing on pure black level, trained on pure black anime images, which causes style shifting, losing details, sometimes deformed faces and backgrounds. This LoRA is trained on a sub dataset of "", only low brightness real world images. - The dataset is big (~400 images), and very diverse. - Only environment, no human in dataset. So it will not "pollute" your characters style. Can be applied on both pure anime and realistic models. - It's dark, not black. The training images still have a quite wide brightness range and are full of details. E.g. cityscape at night and full of small building lights. So the model will know what it should do, just go dark, rather than go crazily black. You will not get deformed bodies, faces or backgrounds. Instead, it makes the dark environment more stable, and adds more details. Useful if you: - want something very dark, darker than prompts can achieve. - want to lower the overall brightness and create a photography feeling. Trained on illustrious v0.1, but I tested it on NoobAI as well. The effects are very good. So I don't think we need a separated NoobAI version.
2,246 téléchargements · 310 j'aime sur Civitai
SHA256
583A239AFED099B568A32127AE5BF4606711641C68505596A0B88D2289627EAC
ID de modèle ModelTrends.ai
#19524
Signaler le contenu
Rendus d'exemple
Prompts et réglages partagés par les personnes qui ont réalisé ces rendus sur Civitai. Choisissez un rendu pour voir comment il a été fait.
Réglages
Sampler
Euler a
Étapes
25
Guidance
4
Seed
1283642035
Taille
832x1216
Prompt
<lora:illustriousXLv01_stable_dark_v0.3:0.9><lora:noobai_ep11_stabilizer_v0.205_fp16:1>1girl,frieren,sunglasses,cigar in mouth,gold chain around neck,white shirt,black suit,sitting on sofa,dark room,dark,smoking,
Réglages
Sampler
Euler a
Étapes
30
Guidance
4.5
Seed
2040760810
Taille
896x1152
Prompt
<lora:noobai_ep11_stabilizer_v0.205_fp16:0.8><lora:style_strength_controller_nbep11_v1:0.2><lora:illustriousXLv01_stable_dark_v0.3:0.6>1girl,fox ears,red eyes,white hair,red hair,closed mouth,multicolored hair,upper body,from side,light particles,falling petals,ambient light,sunset,looking down,cloud,holding flower,hand up,depth of field,wind,land,
Réglages
Sampler
Euler a
Étapes
25
Guidance
4
Seed
2
Taille
864x1152
Prompt
<lora:contract_controller_illus01_v1:0.1><lora:illustriousXLv01_stable_dark_v0.3:0.8><lora:noobai_ep11_stabilizer_v0.205_fp16:1>1girl,fox ears,upper body,red eyes,white hair,red hair,closed mouth,multicolored hair,red whisker markings,from side,sky,snowing,night,dark,masterpiece,
Réglages
Sampler
Euler a
Étapes
30
Guidance
5
Seed
1
Taille
864x1152
Prompt
<lora:noobai_ep11_stabilizer_v0.205_fp16:0.8><lora:stable_dark_nbep10_v0.3:0.8>1girl,fox ears,red eyes,half-closed eyes,white hair,multicolored hair,long hair,whisker markings,upper body,dark,mugshot,anger vein,closed mouth,black shirt,shadow,masterpiece,
Réglages
Sampler
Euler a
Étapes
25
Guidance
4
Seed
1283642035
Taille
832x1216
Prompt
<lora:illustriousXLv01_stable_dark_v0.3:0.9><lora:noobai_ep11_stabilizer_v0.205_fp16:1>1girl,frieren,sunglasses,cigar in mouth,gold chain around neck,white shirt,black suit,sitting on sofa,dark room,dark,smoking,
Réglages
Sampler
DPM++ 2M Karras
Étapes
35
Guidance
4
Seed
1001707729819183
Taille
832x1216
Prompt
1boy, solo, wereshark, shark, (null-ghost:0.7), (lindong:0.6), (oil painting \(medium\):1.2), chiaroscuro, painterly, painting \(medium\), scar, (yellow eyes:0.8), shark tail, (huge muscle, strongman waist, huge arms, slightly chubby), plate armor, red cloak,full body, dutch angle, standing, dynamic pose, holding greatsword, head tilt, castle in background, cloudy sky, battle ground, sunlight, BREAK masterpiece, best quality, amazing quality, very aesthetic, year 2024, newest, highres, absurdres, very awa
Prompt négatif
worst aesthetic, worst quality, low quality, bad quality, old, jpeg artifacts, bad hands, mutated hands, deformed, lowres, (signature, username, logo), embedding:unaestheticXL_cbp62 -neg
Réglages
Sampler
Euler a
Étapes
24
Guidance
5
Seed
1429386309
Taille
1536x640
Prompt
<lora:illustriousXLv01_stable_dark_v0.3:0.2><lora:illustriousXLv01_stabilizer_v1.121:0.6>1girl,frieren,long hair,upper body,ambient light,ocean,cloud,in sky,sunset,masterpiece,
Modèles d'IA pour générer image, vidéo et texte
dark ill xl est un LoRA pour la famille Stable Diffusion XL 1.0, référencé sur ModelTrends.ai, un catalogue en lecture seule de modèles d'IA open source pour l'image, la vidéo et le texte. Comparez-le aux autres modèles Stable Diffusion XL 1.0, consultez son score de chaleur pour suivre sa tendance et ouvrez-le sur PirateDiffusion ou BitVector pour l'essayer.
Parcourir par famille de modèles
Voir tous les modèles