Exécuter en local
charturnerv2.pt
PickleTensor · fp16 · full
Les téléchargements sont servis par Civitai. Certains créateurs demandent d'abord une connexion à Civitai.
À propos de ce modèle
STABLE DIFFUSION 1.5 · Embeddings
Character Turnaround helper by Mousewrites assists in the creation of a consistent character at every angle. It works even better when paired with controlnet poses. This is version 2.0. Tips: render with the /wide command to get more turns. Place the trigger at the beginning of your prompt to boost the effect and then prompt like "a character turnaround of (x) wearing (y), multiple views of the same character in the same outfit". Note: It is not a flawless Textual Inversion, you may still encounter style variations.
Notes du créateur
CharTurner
Edit: controlNet works great with this. Charturner keeps the outfit consistent, controlNet openPose keeps the turns under control.
Three versions, scroll down to pick the right one for you.
If you're unsure of what version you are running, it's probably 1.5, as it is more popular, but 2.1 is newer and gaining ground fast.
Version 2, for 2.0 and 2.1 models
Version 2, for 1.5 models
Version 1, for 1.5 models
BONUS: LORA released
used at your own risk. :D (mixes well tho)
Hey there! I'm a working artist, and I loathe doing character turnarounds, I find it the least fun part of character design. I've been working on an embedding that helps with this process, and, though it's not where I want it to be, I was encouraged to release it under the principle.
I'm also working on a few more character embeddings, including a head turn around and an expression sheet. They're still way too raw to release tho.
Is there some type of embedding that would be useful for you? Let me know, i'm having fun making tools to fix all the stuff I hate doing by hand.
v1 is still a little bit... fiddly.
-
Sampler: I use DPM++ 2m Karras or DDIM most often.
-
Highres. fix ON for best results
-
landscape orientation will get you more 'turns'; square images tend toward just front and back.
-
I like to make characters in.
-
I use an embedding trained on my own art (smoose) that I will release if people want it? But it's an aesthetic thing, just my own vibe.
-
I didn't really test this in any of the waifu/NAI type models, as I don't usually use them. Looks like it works but it probably has its own special dance.
Things I'm working on for v2: EDIT: V2 out, see below! (also v2 2.1)
-
It fights you on style sometimes. I'm adding more various types of art styles to the dataset to combat this. - V2 has much better styles
-
Open front coats and such tend to be open 'back' on the back view. Adding more types of clothing to the dataset to combat this. - Still has this problem
-
Tends toward white and 'fit' characters, which isn't useful. Adding more diversity in body and skin tone to the dataset to combat this. - v2 Much more body and racial diversity added to the set, easier to get different results.
Helps create multiple full body views of a character. The intention is to get at least a front and back, and ideally, a front, 3/4, profile, 1/4 and back versions, in the same outfit.
Mots déclencheurs
charturnerv2
SHA256
A91B570185766FF71F242F83D5BEB6D658348900EDB706A2092BA23D6E1E2CF8
ID de modèle ModelTrends.ai
#6621
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
7.5
Seed
984586396
Taille
832x1216
Clip skip
2
Poids utilisé
1
Prompt
hyper detailed image, 4k, huge masterpiece, huge detail, high detail throughout, 90s anime aesthetic, 1 man, alone, eikichi_onizuka, black elegant suit, black elegant pants, (short yellow hair), ear piercing, (athletic body: 1.3), detailed eyes, detailed face, detailed limbs, detailed hands, the man is on top of a skyscraper, (greeting the audience with a thumbs up and an overexaggerated smile and with money in his hand), smoking a cigar in his mouth, BREAK, in the background, (buildings: 1.5), (clouds), skyscrapers, action lines, pure passion, signal tower, two vanishing points,
Prompt négatif
Deformed hands, poor anatomy, extra fingers, small details, deformed eyes, deformed buildings, extra limbs, missing limbs, functional clothing, functioning limbs, poor scenery, mega deformed, no five vanishing points,
Réglages
Sampler
DPM++ 2M
Étapes
25
Guidance
4
Seed
1230919284
Taille
832x1216
Clip skip
2
Poids utilisé
1
Prompt
A HQ illustration of (poison ivy)! vines, creepers, crawlers, thorns, thistles. hot, humid, depressing atmosphere, depths of a lush jungle, wet, miserable, intricately detailed on every leaf, cinematic lighting, sharp, 4k. taken with a Canon EOS-1D X Mark III fitted with a Sigma 14-24mm f/2.8 DG HSM lens. ((looking at the viewer))
Prompt négatif
(low quality:1.3), (worst quality:1.3)
Réglages
Sampler
Euler
Étapes
25
Guidance
3.5
Seed
1877362716
Taille
832x1216
Clip skip
2
Poids utilisé
1
Prompt
score_9, score_8_up, score_7_up, surrealism. fantasy, complex 3d render of beautiful mesmerising biomechanical cyborg girl 25 years old, on her head, Indian headdress, long blonde hair braided, super facial detailing, with porcelain face, beautiful natural light, diamond shine, sharp graphics, clear pattern, shining eyes big, clear, pearl skin highlighting, 150mm lens, Aztec warrior, steampunk, silver and gold filigree details, alexander mcqueen high fashion haute couture, pearl earring, art nouveau fashion embroidered, hexagonal mesh, Mandelbrot fractal, facial muscles, wires, microchip, elegant, beautiful natural light, studio light, rim light, highly detailed, hyper realistic, sharp, octane render, figure V3, by Luis Royo WLOP, Artgerm, James Jean, Alphonse Mucha, style, art Deco, datanoshing, ink v3, splash style, abstract Art, abstract Tech, 3D h. r. giger style, volumetric lighting, 32k post production
Prompt négatif
smooth, clean, minimalist, sleek, modern, photorealistic, (nsfw, nipples:1.2), text, (watermark:1.3), plastic, deformed body, deformed face, extra limbs, deformed hands, fuzzy, frame, bad eyes, cgi, airbrushed, clones, long neck, multible heads, wrong proportions, freckles, mole, sword, helmet, , muscular female, censored, child, canvas, border, (overexposed:1.2), shiny skin, open mouth, teeth, mutation, bad hands, unnatural hands
Réglages
Sampler
Euler a
Étapes
24
Guidance
10
Seed
222027013
Taille
832x1216
Clip skip
2
Poids utilisé
1
Prompt
score_9,score_8_up,score_7_up, rating_safe, source_anime BREAK, bed, bed room, on side, blush, horny, romantic, sexy, pose, sexy, lewd,
Ultra-high-detailed Anime illustration of Hinata Hino from the anime Mirai Nikki. The artwork features a Hinata Hino in a bedroom. She is depicted with intricate details showcasing her large breasts, and feet. She is 23 years old.
Hinata Hino is looking at the viewer with open brown eyes. She has short brown hair, short hair with long locks, sidelocks, styled in straight hair, floating hair, shiny hair. navel, midriff. cleavage and bare shoulders. The artistic style is intricate_details_xl with a focus on NSFW elements. The color palette emphasizes brown and black, with detailed brush strokes to bring out the character's features. The lighting creates dramatic shadows and highlights, adding depth to the artwork. The perspective is from a slightly elevated angle to enhance the impact of the character's expression. This masterpiece is a true portrayal of Hinata Hino's complex personality and will captivate any fan of Mirai Nikki. uncensored,hino_hinata, Hinata
Prompt négatif
3d, monochrome, worst quality, low quality, bad hands, bad fingers, mutated hands, long fingers, deformed hands, missing leg, (missing arm), (missing hand), missing feet, missing limbs, anatomical nonsense, bad arm position, bad leg position, bad limb position, extra leg, extra arm, extra limbs, disconnected limbs, disconnected legs, disconnected arms, fused limbs, fused fingers, fused legs, fused arms, bad proportions, bad fingers, bad-hands, black, lace, worst quality, low quality, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, normal quality, wrong hair color, jpeg artifacts, signature, watermark, username, blurry, only feet, missing face, only certain part of body, worst hands, bad outfits, muscles, made up, makeup, artificial eyelashes, fake breasts, wearing clothes, blurry clothes, poorly drawn eyes, mutated eyes, deformed iris, deformed pupils, worst quality pupils, missing eyebrows, out of frame
Réglages
Sampler
Euler
Étapes
8
Guidance
1
Seed
712775273
Taille
832x1216
Clip skip
2
Poids utilisé
1
Prompt
((marching)), three quarters view,
Stone catacombs in an alien world . Alien stone military tank,
fissures on skin
((((Full body portrait))))
Prompt négatif
score_6, score_5, score_4, skinny, anorexic, furry, (loli, child), muscular body, small breast,low detailed face, asian, bad face, ugly face, mutated hands, negative_hand, (polydactyly:1.2), (polydactyl:1.2), bad fingers, (milf:1.3), ugly nose, bad nose, signature, watermark, comics, frames, completely naked, digital art, 2d, completely naked, ((closeup:1.4)), static pose, static, fantasy:1.4, ((front shot:1.2, face focused)), see-through, navel, woman, girl, midget, dwarf, children, short people
Réglages
Sampler
DPM++ 2M
Étapes
32
Guidance
6
Seed
1569119546
Taille
832x1216
Clip skip
2
Poids utilisé
1
Prompt
detailed background,( warm spring landscape), Riverside Street, Cherry tree in full bloom, Cherry blossom trees, day, dappled sunlight, tranquil river, charming cafes, outdoor seating, depth of field, masterpiece, best quality, ultra-detailed, very aesthetic, illustration, perfect composition, intricate details, absurdres, moody lighting,
Prompt négatif
longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, very displeasing, blurry, artist name, huge breasts,
Modèles similaires
Modèles d'IA pour générer image, vidéo et texte
char turner est un embedding pour la famille Stable Diffusion 1.5, 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 1.5, consultez son score de chaleur pour suivre sa tendance et ouvrez-le sur PirateDiffusion ou BitVector pour l'essayer.
Plus de modèles Stable Diffusion 1.5Plus de Embeddings Stable Diffusion 1.5gamingposes3dclothingconsistent characterturnaroundmodel sheettool
Parcourir par famille de modèles
Modèles Text / LLM
411
Modèles Anima
509
Modèles Chroma
14
Modèles Flux
1,071
Modèles Flux 2 / Klein
1,237
Modèles MiniMax H3
331
Modèles Hunyuan
197
Modèles Ideogram
20
Modèles Krea2
674
Modèles Qwen
17
Modèles Qwen2
36
Modèles Ltx2
150
Modèles Stable Diffusion 1.5
6,465
Modèles Stable Diffusion XL 1.0
15,432
Modèles Zimage
804
Modèles Wan
919

Model
Trends
.ai
© ModelTrends.ai
|
Fabriqué au Japon
|
© 2026
