Exécuter en local
VestalWater_Illustrious_v2_000004500.safetensors
162 MB · SafeTensor
Les téléchargements sont servis par Civitai. Certains créateurs demandent d'abord une connexion à Civitai.
À propos de ce modèle
ZIMAGE · LoRA
by VestalWater - VestalWater's Illustrious Styles for Z-Image-Turbo
Notes du créateur
Overview
This is the Z-Image-Turbo version of my lora. This LoRA aims to make ZIT's output look more like images from an Illustrious finetune.
If you like my work, please consider supporting me at .
Why use Z-Image-Turbo + an Illustrious Lora over Illustrious alone? ZIT has great prompt adherence and handles complex prompts really well, but it doesn't render images with the most flattering art style. Illustrious is the opposite: It has a great art style and aesthetics but struggles as soon as the prompt demands complex subject positions and specific elements to be present in the composition.
This lora aims to capture the best of both worlds, ZIT’s understanding of complex prompts and the lora adds a (subjectively speaking) flattering art style on top of it.
V2 is out!
VestalWater's V2 Lora is out! This new version features the following improvements:
-
Completely new dataset using extremely cherry picked illustrious images. This results in a far more coherent background and significantly less hallucinatory and messy lines in the background.
-
The new dataset also removes the weird striations on women's skin.
-
Used version 2 of Ostris' Training Adapter which should make the model understand the concept better
Comparison between v1 and v2
Same prompt, not cherry picked, keep in mind the turbo version of ZIT has a problem with hands. High res comparison link:
V2
V1
Settings and Workflow
All images in the image carousel have ComfyUI workflows attached.
TLDR:
Sampler: ER_SDE (Please don't use euler simple. It's so bad for illustrations.)
Scheduler: Simple
Lora Strength: 0.8
Steps: 8
CFG: 1
SHA256
61A2D951542E92D3C90F72BEF1744239AD62B52F4242B71F4477C97AB2772670
ID de modèle ModelTrends.ai
#24049
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
er_sde
Étapes
8
Guidance
1
Seed
947024443700865
Taille
1104x1696
Prompt
A woman wearing grey sweatshorts, a loose black hoodie with the hood up, long brown hair. She possesses a sculpted hourglass figure. Her hoodie is unzipped, revealing her navel and a loose white cropped t-shirt.
Setting: A dim, neon-lit server room filled with cables and blue light. She is posing, and pressed back against a wall of monitors.Action: She is pulling one of the cables playfully between her teeth while looking up through her lashes.
looking to the side.
Text Integration: One of the monitors directly next to her head displays the text "Cloudflare Status: REDUCED CAPACITY" in bold, flashing orange distinct letters.
Réglages
Sampler
Undefined
Étapes
8
Guidance
1
Seed
979978428
Taille
832x1216
Clip skip
2
Poids utilisé
0.75
Prompt
in the style of cksc,
(shallow depth of field:1.4), Chiaroscuro Lighting Style, (Masterpiece:1.4), (high quality:1.2), (best quality:1.2),2boy, 1girl, solo, polka dot dress, wh1tep0lkadr3ss, White_ Polka Dot Dress, sitting, high heels, crossed legs, office chair, office, indoors, computer. desk, arms behind head, (fluorescent floor by night:1.1), Head tilt, tilting her head slightly to one side, suggestive smile on her face, phosphorescent water, glowing white floor, glowing, glowing neon,, flirt,(glowing-neon-white uniform, glowing neon white thighhighs, ), stiletto heels, perfect body, detailed skin, subsurface scattering, oily skin, glossy skin, classic hair style, elegant hair style, swept-back hairstyle, , minimalistic fashion portrait, stark lighting, medium-format camera, bold posing, emphasizing high fashion, dramatic lighting, fashion photography, art by Richard Avedon, . unimaginable quality,..
8K... .masterpiece,
Réglages
Sampler
Undefined
Étapes
9
Guidance
1
Seed
1613746891
Taille
832x1216
Clip skip
2
Poids utilisé
0.8
Prompt
A stylized digital illustration in comic line art style, rendered with professional, sleek, modern precision through vector graphics and graphic novel aesthetics. Employ a minimalist palette dominated by deep, enveloping shadows and negative space to evoke enigmatic stillness and cinematic tension, contrasted by saturated, vibrant highlights faint red edge-lighting grazing contours, intense glowing accents piercing the darkness, and subtle glints of reflection along sharp, clean thick lines. Build quiet suspense with highly detailed yet restrained compositions, emphasizing stark contrasts between obscurity and luminous presence for a vibrant, graphic, and immersive visual impact.
Harley Quinn, clean lineart, cel-shaded, vibrant colors, soft shading, illustrious, close up portrait , flat colors, blue eyes, blonde two-tails red-blue colored hair, 1girl, detailed face, perfect face,dramatic light, @>2=K9 B>= :>68, portrait, crop top, H:>;L=0O D>@<0, A8=OO D>@<0, , AB>8B C AB>;10, :@KH8 4><>2 8 ?@>2>40, A<>B@8B 225@E, , @N:70:, <8;0O C;K1:0, :@0A820O ?>70, AB@>9=>5 B5;>, 15;K5 3>;LDK 2 ?>;>A:C, 25G5@, 25G5@=89 A25B, 75@=8AB>ABL, small breasts, ?>?@02;O5B 2>;>AK, 70AB5=G820O C;K1:0, @C<O=5F,
Prompt négatif
bad, ugly,
Réglages
Sampler
er_sde
Étapes
8
Guidance
1
Seed
45295159370463
Taille
1104x1696
Prompt
A brown-haired woman with an excited smile, wearing a black and white race suit and shorts, sits on a black sports car, holding a skull flag, at a race track.
Holding a flag with both hands. One leg is raised up and resting on the sports car.
Tyre of the sports car is visible.
Prompt négatif
yellow tint, color grading, plastic surgery, overly thick lips, full lips, botched plastic surgery, extra fingers, missing fingers, three hands,
Réglages
Sampler
Undefined
Étapes
9
Guidance
1
Seed
1083180411
Taille
832x1216
Clip skip
2
Poids utilisé
0
Prompt
A stylized digital illustration in comic line art style, rendered with professional, sleek, modern precision through vector graphics and graphic novel aesthetics. Employ a minimalist palette dominated by deep, enveloping shadows and negative space to evoke enigmatic stillness and cinematic tension, contrasted by saturated, vibrant highlights faint red edge-lighting grazing contours, intense glowing accents piercing the darkness, and subtle glints of reflection along sharp, clean thick lines. Build quiet suspense with highly detailed yet restrained compositions, emphasizing stark contrasts between obscurity and luminous presence for a vibrant, graphic, and immersive visual impact.
Harley Quinn, clean lineart, cel-shaded, vibrant colors, soft shading, illustrious, close up portrait , flat colors, blue eyes, blonde two-tails red-blue colored hair, 1girl, detailed face, perfect face,dramatic light, @>2=K9 B>= :>68, portrait, crop top, H:>;L=0O D>@<0, A8=OO D>@<0, , AB>8B C AB>;10, :@KH8 4><>2 8 ?@>2>40, A<>B@8B 225@E, , @N:70:, <8;0O C;K1:0, :@0A820O ?>70, AB@>9=>5 B5;>, 15;K5 3>;LDK 2 ?>;>A:C, 25G5@, 25G5@=89 A25B, 75@=8AB>ABL, small breasts, ?>?@02;O5B 2>;>AK, 70AB5=G820O C;K1:0, @C<O=5F,
Prompt négatif
bad, ugly,
Réglages
Sampler
er_sde
Étapes
8
Guidance
1
Seed
93101824420897
Taille
1104x1696
Prompt
Sexy secretary outfit. A woman with long brown hair, showing an excited, flushed smile. She leans forward on a wooden desk in a modern office with large windows overlooking a city skyline.
Réglages
Sampler
er_sde
Étapes
8
Guidance
1
Seed
456323934450114
Taille
1104x1696
Prompt
A woman with brown pigtails, wearing a blue jacket over a white t-shirt, with snacks hidden in her jacket, posing in an airplane cabin. Fisheye lens effect.
Prompt négatif
yellow tint, color grading, plastic surgery, overly thick lips, full lips, botched plastic surgery, extra fingers, missing fingers, three hands,
Modèles similaires
Badges for creators
Made this model? Put its standing on your Civitai page, your Hugging Face card, your README or your site. Each badge is a small picture that shows the standing on the day you copy it and never changes afterwards, however the rankings move later. The date is part of the badge.
Modèles d'IA pour générer image, vidéo et texte
vestalwaters2 zit est un LoRA pour la famille Zimage, 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 Zimage, consultez son score de chaleur pour suivre sa tendance et ouvrez-le sur PirateDiffusion ou BitVector pour l'essayer.
Parcourir par famille de modèles
Modèles Text / LLM
415
Modèles Anima
519
Modèles Chroma
15
Modèles Flux
1,495
Modèles Flux 2 / Klein
1,238
Modèles MiniMax H3
330
Modèles Hunyuan
204
Modèles Ideogram
20
Modèles Krea2
676
Modèles Qwen
20
Modèles Qwen2
36
Modèles Ltx2
152
Modèles Stable Diffusion 1.5
7,027
Modèles Stable Diffusion XL 1.0
17,373
Modèles Zimage
815
Modèles Wan
1,244
Model
Trends
.ai
© ModelTrends.ai
|
© 2026
|
Tous droits réservés