Model
Trends
.ai
Model
Trends
.ai
les meilleurs modèles d'IA open source
Exécuter en local
chiaroscuro_illus01_2a.safetensors
337 MB · SafeTensor
Les téléchargements sont servis par Civitai. Certains créateurs demandent d'abord une connexion à Civitai.
AD
<low-light-xl>
À propos de ce modèle
STABLE DIFFUSION XL 1.0 · LoRA
Créé par
phoenician
sur Civitai
by phoenician - Low Light, Dark, Chiaroscuro for Illustrious 0.1 & NoobAI
Notes du créateur
For version 2 I went through the dataset and applied photoshop to each image, generally speaking splitting the image into 3 layers, setting the top layer to luminance only, then tuning brightness and opacity, then color and opacity on middle layer to modestly stretch contrast while preserving tone and saturation. The Noob VPred 1.0 version is not as straightforward of an effect, because the base model is already capable of strong contrast and darker images. So this version helps promote contrast, shadow detail, and lower light levels. Helps your pictures not be so damn bright. Trained on Illustrious 0.1 for now for broad compatibility. Tested on Noob 1.0, at 1.0 power. I looked for a lot of dark images with good shadow detail and contrast, less than peak brightness on highlights, and lower average luminance. To use: load the lora, and use tags like dark, , moonlight, dark background, black background, etc to shape how bright your picture is. Dark and chiaroscuro are the two big tags, and I specifically included some moonlight pictures for nice highlights at night when you want them.
Mots déclencheurs
chiaroscuro
dark
2,202 téléchargements · 357 j'aime sur Civitai
SHA256
237AFBEC39ED248596FCFBA15E668319A2571C8F09B0D4B1394E23023CE19E7A
ID de modèle ModelTrends.ai
#14881
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
DPM++ 2M
Étapes
30
Guidance
4
Seed
124542586575093
Taille
1184x1744
Prompt
masterpiece, best quality, ultra-detailed, 8k resolution, high dynamic range, absurdres, stunningly beautiful, intricate details, sharp focus, detailed eyes, cinematic color grading, high-resolution texture, photorealistic, 1woman, mature female, red hair, long hair, blue eyes, spider-man suit, bodysuit, squatting, head tilt, hand on own cheek, head rest, laooking at viewer, parted lips, night, city lights, rooftop, skyscrappers, new york city, superhero, large breasts, chromatic aberration, distortion effect, spider web
Prompt négatif
worst_quality, bad_quality, poorly_detailed
Réglages
Sampler
Euler a
Étapes
30
Guidance
6.5
Seed
264588282
Taille
1280x1856
Clip skip
2
Poids utilisé
0.5
Prompt
safe_pos, yin (darker than black), 1girl, purple eyes, grey hair, white hair, long hair, ponytail, large feathered demon wings,(contrapposto:1.0), dark background, cinematic shot, chiaroscuro,dark, dark aura, halo, ray tracing, solo, white white elbow gloves, black high heels, necklace, white evening gown, emotionless expression, cold gaze, ballroom, indoors, depth of field, full body, sitting, chair, flower, erotic composition, holding cup, wine glass, from side, looking at viewer, window, night, starry sky, dynamic light, vibrant colors, eye-catching, colorful, detailed eyes, face, textured surfaces, depth of field, dramatic shadows, rich details, detailed background, dynamic angle,professional lighting, detailed environment, masterpiece, best quality, very awa, absurdres, very aesthetic, newest, (by happoubi jin:0.3), (by naokomama:0.4), (by dk.senie:0.3),(by gabiran:0.2), (by darjeeling (reley):0.3),(by ibuki notsu:0.3), (by sakuraba yuuki:0.2), (by nagishiro mito:0.6), (by guweiz:0.8),
Prompt négatif
safe_neg, Lowres, (bad), bad anatomy, bad hands, deformed hands, extra fingers, extra digits, multiple views,fewer, extra, worst quality,low quality, watermark, unfinished, displeasing, multiple views, simple background,
Réglages
Sampler
Euler a Karras
Étapes
30
Guidance
3
Seed
736426169543112
Taille
1664x2432
Clip skip
2
Prompt
masterpiece, best quality, amazing quality, Smooth Quality, artist:moriimee, j1nr0h, mature, dark_fantasy_illustration, realistic, 1girl, solo, hunkRE, helmet, glowing eyes, faceless, (black background), abstract background, standing, latex bodysuit, ((slim body)), (big breasts:0.8), red glow, athletic body, (shoulder armor:0.8), plastic gauntlets, torso armor, armor bra, armor thongs, highleg, leg armor, stomach armor, straps, (low contrast), dark, pointing finger at viewer, threatening, (straight-on), brick, (cleft of venus:0.7).<lora:il\StS-Illustrious-Detail-Slider-v1.0.safetensors:4.0:4.0> <lora:xl_more_art-full_v1.safetensors:0.6:0.6> <lora:il\JinRohWolfBrigadeILXL.safetensors:0.8:0.8> <lora:il\MoriiMee_Gothic_Niji_Style_Illustrious_r1.safetensors:0.6:0.6> <lora:il\HUNK_ResidentEvil_V1_ILXL.safetensors:0.5:0.5> <lora:il\chiaroscuro_illus01_2a.safetensors:0.7000000000000001:0.7000000000000001> <lora:il\dark_fantasy_illustration_illustriousXL.safetensors:0.4:0.4>
Prompt négatif
bad quality, worst quality, worst detail, sketch, censored, monochrome, child, fat, anime, (text)
Réglages
Sampler
DPM++ 2M SDE
Étapes
30
Guidance
5
Seed
1082880186467960
Taille
2144x3136
Prompt
embedding:lazypos_v2, 1woman, mature female, auburn hair, long hair, witch hat, white tunic, striped tunic, leather corset, cross-laced corset, yellow cape, brown skirt, layered skirt, overskirt, multiple belts, floating clothes, cauldron, colored bubbles, holding book, spellbook, face tattoo, glowing hand, casting spell, outstretched arm, candles, potions, witch workshop, from below, northern light, window, night, dark
Prompt négatif
embedding:lazyneg_v3, embedding:lazyloli, embedding:lazyhand
Réglages
Sampler
DDIM
Étapes
30
Guidance
6
Seed
1946789607
Taille
1280x1856
Clip skip
2
Poids utilisé
1
Prompt
safe_pos, score_9, score_8_up, score_7_up, masterpiece,source_anime, best quality, perfect anatomy, very aesthetic, ((outlined outlined vector graphics)), score_anime # Character 21yo,1girl,(solo),solo focus,(focus female),original,female focus, black hair,long hair, hair ornament, single braid,muscular, medium breast,close up,full body # Lora valkyrie, valkyrie dress, armor, sword, holding sword, ultra instinct,aura, glowing, glittering, glimmering, # Motif looking at viewer,expressionless, whimsical anime background, soft diffused lighting, gentle ambient light, no harsh shadows,natural light,indoor,chamber # Special pureerosface_v1 chiaroscuro,dark
Prompt négatif
civit_nsfw, safe_neg, lowres, worst quality, bad quality, quality, low quality, normal quality, footer,footer text,jpeg artifacts, signature, watermark, username,bad hands ,bad foots easynegative,ng_deepnegative_v1_75t,negative_hand ,bad_prompt_version2, NegfeetV2
Réglages
Sampler
Euler
Étapes
28
Guidance
5
Taille
1280x1856
Clip skip
2
Poids utilisé
0.6
Prompt
1girl, izumi konata, lucky star, :3, a flat chest is a status symbol, closed mouth, green eyes, blue hair, huge ahoge, double-parted bangs, grey background, hair between eyes, hand on own hip, long hair, mole, mole under eye, puff of air, shirt, short sleeves, simple background, smile, solo, upper body, white shirt, masterpiece, best quality, amazing quality, very aesthetic, newest, absurdres, scenery, very awa, soft colors, dynamic lighting, soft shadows, (official art:1.1), chiaroscuro,
Prompt négatif
bad quality, worst quality, worst detail, sketch, (censor:1.1), (shaded face:1.2), shiny skin,
Modèles d'IA pour générer image, vidéo et texte
low light 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