Model
Trends
.ai
Model
Trends
.ai
les meilleurs modèles d'IA open source
Exécuter en local
DarkDarkest.safetensors
193 MB · SafeTensor
Les téléchargements sont servis par Civitai. Certains créateurs demandent d'abord une connexion à Civitai.
À propos de ce modèle
STABLE DIFFUSION XL 1.0 · LoRA
Créé par
Mexes
sur Civitai
by Mexes - Dark Darker Darkness | Mexes Illus v1.0
Notes du créateur
I accept LoRA training commissions for both Anima and Illustrious! If you are interested, you can find more information at the following link: Anima V0.1 Details trigger word: dark, darkness, black background V2.0 DETAILS Trigger word: d4rk, dark, darkness V1.0 DETAILS I wanted the V1.0 Lora not to affect the style—only to change the lighting. It was trained with different styles to achieve this, so now this version simply makes the scene darker, minimally affecting the style. I also wanted the light sources to work better, which means the darkness isn’t as deep since the lights stand out more—but it paves the way for more cinematic generations. You can always revert to the previous version if you like. Keyword: The Lora itself doesn’t have a keyword, but you can use dark, darkness, dark background to intensify the effect. Training: It was trained on 130 images that were upscaled, inpainted, and batch-edited to adjust gamma and even out scene contrast, plus a few manually fine-tuned. Issues: I noticed the Lora’s effect diminishes when too many tags are used, so keep it simple. If that’s not possible, add some extra tags. Also, using distinct light sources like candlelight can help improve the effect.
Mots déclencheurs
dark
darkness
864 téléchargements · 159 j'aime sur Civitai
SHA256
6B41883716459E54062BB22D0CBA69344F9A790F08E07453875B3F8EC285643E
ID de modèle ModelTrends.ai
#15368
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
30
Guidance
5
Seed
1931010023
Taille
832x1216
Clip skip
2
Prompt
1girl, solo, lazypos, anime-style, delicate, dreamy, ray tracing, dramatic shadows, <lora:hololive_kaela_kovalskia_redebut:0.4> kaela20, blonde hair, red eyes, slightly open mouth, smile, (white shirt, red jacket, hoodie:1.5), upper body, <lora:DarkDarkest:1> dark, darkness, dark background, flashlight, flashlight to face, <lora:USNR_STYLE_ILL:0.5> usnr <lora:WSSKX_WAI:0.3> <lora:TRT_IL:0.65>
Prompt négatif
lazyneg, lazyhand, nsfw, (sweat:1.5), (goggles:1.5), sunglasses, (jewelry:1.5), (earrings:1.5), gem, gemstone, (hair ribbon:1.5), (hair bow:1.5), (earring:1.5), bad perspective, poor lighting, missing limbs, turtleneck shirt, blush
Réglages
Sampler
Euler a
Étapes
28
Guidance
8
Seed
1281767949
Taille
832x1216
Clip skip
2
Poids utilisé
0.8
Prompt
ominous mountain, night, shadows, evening, masterpiece, best quality, highres, 8k, high contrast, very aesthetic, ultra-detailed, extremely detailed, newest, official art, cinematic lighting, sharp focus, vibrant colors, high contrast, perfect shading, dynamic angle, intricate, dark, darkness, fine art parody, faux traditional media, watercolor (medium),
Prompt négatif
lowres, worst quality, low quality, text, logo, artist name, extra digits, sea, human, bystander
Réglages
Taille
896x1152
Prompt
masterpiece, best quality, highres, absurdres, dark, d.va, plaid skirt, pink skirt, pleated skirt, white shirt, collared shirt, neck ribbon, round glasses,
Réglages
Sampler
DDIM CFG++
Étapes
30
Guidance
3
Seed
3480320543
Taille
768x1344
Clip skip
2
Prompt
dynamic angle, 1girl, solo, adult, aged up, furina \(genshin impact\), short hair, heterochromia, mismatched gloves, blue jacket, waist cape, ascot, white waistcoat, waist bow, white shorts, thigh strap, block heels, frilled socks, dancing, standing on one leg, one arm up, spread arms, closed eyes, tears, serious, wet, glowing, reflection, reflective water, water, droplets, splash, water magic, dark, dark background, darkness, masterwork, masterpiece, fantastical, enchanting, best quality, depth of field, high detail, very aesthetic, best quality, amazing quality, absurdres, 8k <lora:Char-Genshin-Furina-V3-IL:0.9> <lora:DarkDarkest:1> <lora:GlowingHairILL:0.7> <lora:ReflectionILL:0.8> <lora:NewFantasyCoreV4_ILL_by_VisionaryAI_:0.9>
Prompt négatif
nsfw, uncensored, 3D, extra fingers, extra hands, extra legs, extra feet, missing fingers, extra arms, bad hands, bad fingers, bad hands, low quality, worst quality, normal quality, ugly, deformed, gross, bad anatomy, bad proportions, jpeg artifacts, artist name, logo, watermark, broken, lowres, abstract, realistic, western, DeepNegative_xl_v1, zPDXLxxx-neg
Modèles d'IA pour générer image, vidéo et texte
dark darker 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