Kör lokalt
darkSushiMixMix_225D.safetensors
1.99 GB · SafeTensor · fp16 · pruned
Nedladdningar sköts av Civitai. Vissa skapare kräver att du först loggar in på Civitai.
Om denna modell
STABLE DIFFUSION 1.5 · Basmodeller
Dark Sushi Mix brighter version by Aitasai This model is good for traditional anime/cartoon renders without adding any additional dimension to them. Compared to the 25 version, the colors are lighter and brighter. Its style may be compared to misstoon.
Skaparens anteckningar
Recommend:
vae-ft-mse-840000-ema
use highres fix to improve quality.
打了一个月王国之泪后重操旧业。
新版本算是对2.5d的整合,保留整体二次元画风的同时肢体上比前几个版本要好,脸型也要更多样化一点。
但光影和线条上就和2.5D更像一些,我也纠结了很久究竟该放在哪边,最终还是放在这了。于是干脆起个2.25d的版本名吧,至于孰好孰坏就见仁见智了。
多少有点背离初衷了,一点都不暗了。想暗的话还是自己加noiseoffset吧
After playing Tears of the Kingdom for a month, I resumed my old work. The new version is an integration of 2.5d, which retains the overall anime style while being better than the previous versions on the limbs, but the light and shadow and lines are more like 2.5D, so i simply call it 2.25d version.
起名废玩烂梗系列,事后想想起的不错。
首先暗图效果比较好,dark合适,自己融的时候差不多也是寿司那样什么都塞点,dark 寿司没毛病。
光效比较好,能生成比较暗的图,正常亮度的图片也有不错的光影表现。
融了群友私模和一大堆我也记不住组成的以前的自融模
能确定包含的是自己之前的五仁和
以及群友的TmndMix ,绝对的杰作,推荐大家都去试试
darker版本里还加了noiseoffset的lora,生图要比brighter版本暗一些,光影表现上要强一点,但缺点就是正常生图也会比较暗。大家一般用brighter版再自己调用noiseoffset的lora也能达到类似效果。
Intro:
named from a dark soul's meme in Chinese community.
merged with my friend's pravite model and some other models merged by myself.
Including ,
and my friend's TmndMix .it's definitely a masterpiece.
if you like dark sushi ,you should also try tmnd.
noiseoffset lora is merged into the darker version. So the imgs generated by the darker version will be darker ,and have better light and shadow performance. you can use brighter version and noiseoffset lora to get similar effect.
SHA256
CCA17B08DA3254AA2F0242A84AB8641C89D1BC71CC1046FC79F8E906581A97BA
ModelTrends.ai modell-ID
#588
Rapportera innehåll
Exempelrenderingar
Prompter och inställningar delade av personerna som gjorde dessa renderingar på Civitai. Välj en rendering för att se hur den gjordes.
Inställningar
Sampler
Euler a
Steg
110
Guidance
7
Seed
3683420320
Storlek
2048x600
Clip skip
2
Prompt
(((masterpiece, detailed:1.3))), virtual, disintegration, wireframe, rgb, translucent, transparent, reflection
Negativ prompt
[( NG_DeepNegative_V1_64T :0.9) :0.1], bad-picture-chill-75v, easynegative,paintings,sketches,(worst quality:2),(low quality:2),(normal quality:2),low res,normal quality,((monochrome)),((grayscale)),skin spots,acnes,skin blemishes,age spot,glans,extra fingers,fewer fingers,strange fingers,bad hand,mole,((extra legs)),((extra hands)),bad-hands-5,hands,Not a medieval setting,No western dragons,No guns,Not in daylight,Not a fantasy landscape,Not a peaceful scene,No male characters
Inställningar
Sampler
DPM++ 2M
Steg
50
Guidance
7
Seed
3378732642
Storlek
512x768
Clip skip
2
Prompt
(1girl), (fantasy style:1.2), (high quality:1.3), (best quality:1.3), (masterpiece:1.3), official art, official wallpaper, 4k textures, epic(1.5), (phoenix woman), blackphoenix, black hair, (detailedfeathers), (fierywings), aggressivepose, midflight, (detailedplumage), glowingeffects, darkbackground, fire, flames, dramaticlighting, fireandicecontrast, (detailed:1.05), (extremely detailed:1.06), sharp focus, (intricate:1.03), (extremely intricate:1.04), (epic scenery:1.09), soothing tones, hdr, (beautiful scenery:1.08), (detailed scenery:1.08), (intricate scenery:1.07), (wonderful scenery:1.05), (beautiful face:1.1), [perfect eyes:0.8], [perfect skin:0.8], [detailed face:0.8], [detailed eyes:0.8], [detailed hair:0.9], [detailed lips:0.8],
Negativ prompt
EasyNegativeV2, (low quality:1.32), (normal quality:1.31), (worst quality:1.33), (bad anatomy), (bad Hands), (mutated limbs:1.2), (mutated hands, mutated fingers:1.2), (deformed hands:1.2), (text:1.5), simple background,
Inställningar
Sampler
DPM++ 2M
Steg
36
Guidance
7
Seed
2774516464
Storlek
671x671
Clip skip
2
Prompt
cinematic anime shot of two female fantasy knights in beautiful armor in a sword fight, fighting each other, holding glowing sword, 1vs1, sword duel, hkstylen anime style
Inställningar
Sampler
DPM++ 2M
Steg
50
Guidance
7
Seed
3378732643
Storlek
512x768
Clip skip
2
Prompt
(1girl), (fantasy style:1.2), (high quality:1.3), (best quality:1.3), (masterpiece:1.3), official art, official wallpaper, 4k textures, epic(1.5), (phoenix woman), blackphoenix, black hair, (detailedfeathers), (fierywings), aggressivepose, midflight, (detailedplumage), glowingeffects, darkbackground, fire, flames, dramaticlighting, fireandicecontrast, (detailed:1.05), (extremely detailed:1.06), sharp focus, (intricate:1.03), (extremely intricate:1.04), (epic scenery:1.09), soothing tones, hdr, (beautiful scenery:1.08), (detailed scenery:1.08), (intricate scenery:1.07), (wonderful scenery:1.05), (beautiful face:1.1), [perfect eyes:0.8], [perfect skin:0.8], [detailed face:0.8], [detailed eyes:0.8], [detailed hair:0.9], [detailed lips:0.8],
Negativ prompt
EasyNegativeV2, (low quality:1.32), (normal quality:1.31), (worst quality:1.33), (bad anatomy), (bad Hands), (mutated limbs:1.2), (mutated hands, mutated fingers:1.2), (deformed hands:1.2), (text:1.5), simple background,
Inställningar
Sampler
DPM++ 2M Karras
Steg
20
Guidance
7
Seed
3655205658
Storlek
1080x1626
Prompt
(masterpiece), (best quality:1.3), 8k wallpaper, smooth gradients, 1girl, clean wall, detailed face, black eyes, realistic eyes, smile
Negativ prompt
easynegative, (worst quality, low quality, normal quality:1.5), nude, nsfw, animals
Inställningar
Sampler
DPM++ 2M Karras
Steg
20
Guidance
8
Seed
1931785963
Storlek
512x832
Clip skip
2
Prompt
masterpiece, best quality, 1girl, (colorful),(delicate eyes and face), volumatic light, ray tracing, bust shot ,extremely detailed CG unity 8k wallpaper,solo,smile,intricate skirt,((flying petal)),(Flowery meadow) sky, cloudy_sky, moonlight, moon, night, (dark theme:1.3), light, fantasy, windy, magic sparks, dark castle,white hair
Negativ prompt
paintings, sketches, fingers, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot, (outdoor:1.6), backlight,(ugly:1.331), (duplicate:1.331), (morbid:1.21), (mutilated:1.21), (tranny:1.331), mutated hands, (poorly drawn hands:1.5), blurry, (bad anatomy:1.21), (bad proportions:1.331), extra limbs, (disfigured:1.331), (more than 2 nipples:1.331), (missing arms:1.331), (extra legs:1.331), (fused fingers:1.61051), (too many fingers:1.61051), (unclear eyes:1.331), lowers, bad hands, missing fingers, extra digit, (futa:1.1),bad hands, missing fingers, bad-hands-5
Inställningar
Sampler
DPM++ 2M Karras
Steg
25
Guidance
7
Seed
761331329
Storlek
512x768
Clip skip
2
Prompt
((masterpiece)), ((best quality)), ((high resolution)), 8k extremely detailed)), full body, only
yuubari kantai collection, ponytail, bangs, brown eyes, hair bow, brown hair, white dress, brown skirt, smile, standing in a field of sunflowers
Negativ prompt
(worst quality, poor quality, poor quality:2), lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, blurred, defective feet, multiple breasts, (mutated hands and fingers: 1.5), disfigured, malformed, mutated, malformed hands, long neck, blurred , inferior, bad proportions, bad shadow, uncoordinated body, unnatural body, fused breasts, defective breasts, badly drawn breasts, extra breasts, missing breasts, huge haunch, huge thighs, fused hand, missing hand, muscles, toned, abs, mosaic censorship
Liknande modeller
AI-modeller för bild-, video- och textgenerering
sushimix är en basmodell för familjen Stable Diffusion 1.5, listad på ModelTrends.ai, en skrivskyddad katalog över AI-modeller med öppen källkod för bild, video och text. Jämför den med andra Stable Diffusion 1.5-modeller, se dess hettapoäng och prova den på PirateDiffusion eller BitVector.
Fler Stable Diffusion 1.5-modellerFler Stable Diffusion 1.5 Basmodelleranimecartoonsdrawings3dfoodbasebase model
Bläddra efter modellfamilj
Text / LLM-modeller
411
Anima-modeller
509
Chroma-modeller
14
Flux-modeller
1,071
Flux 2 / Klein-modeller
1,237
MiniMax H3-modeller
331
Hunyuan-modeller
197
Ideogram-modeller
20
Krea2-modeller
674
Qwen-modeller
17
Qwen2-modeller
36
Ltx2-modeller
150
Stable Diffusion 1.5-modeller
6,465
Stable Diffusion XL 1.0-modeller
15,432
Zimage-modeller
804
Wan-modeller
919

Model
Trends
.ai
© ModelTrends.ai
|
Tillverkad i Japan
|
© 2026







