로컬에서 실행
M4RV3LSDUNGEONSNEWV40COMICS_mD40_102885.safetensors
1.99 GB · SafeTensor · fp16 · pruned
M4RV3LSDUNGEONSNEWV40COMICS_mD40_102301.safetensors
3.95 GB · SafeTensor · fp16 · full
다운로드는 Civitai에서 제공합니다. 일부 제작자는 먼저 Civitai 로그인을 요구합니다.
이 모델에 대하여
STABLE DIFFUSION 1.5 · 베이스 모델
M4RV3LS & DUNGEONS - v4.0 by DarkAgent is a full model, a checkpoint merge of many popular comics models. Creator notes: "A hand selected collection of the best of the best, no compromise models to make up this collection! Specializes in traditional Western Style Comic Characters 2D-2.5D Semi-Realistic, Illustrations & Fantasy Art! Will do everything from sketch designs, to full comic posters, character concepts, panel layouts, complex scenery, fantasy art of all kinds, sci-fi, retro, etc. The results are endless! From 2D to Boris Vallejo Paintings and other artists this will do almost everything with a bit of prompt crafting! It also works with LORAs & EMBEDS without difficulty and generates some very unique and interesting results. (Can't guarantee every LORA will work with it. but many I've tried seem to without issue.) It's created to be a catch all for this particular medium and I've tested this model for a month exclusively and have been very impressed with its results."
제작자 노트
> VERSION 3.0 NOW AVAILABLE! FULL & PRUNED VERSIONS 🌟WORKS BEST WITH CLIP SKIP 1! 🌟 select the face or eyes > lower the denoise strength to 0.5-0.57. > make sure your seed is set to random.
masked content = fill / inpaint area = whole picture ====== for faces
masked content = fill / inpaint area = only masked ====== for eyes
With "whole picture" selected for larger inpaint target aka faces (or hands) you may need the denoise to be lower to pick up more of the original image. 0.53-0.56
Now with "only masked" and a smaller target like eyes you get a little more freedom so your denoise can be 0.54-0.57
Run a batch of 4-5 (or more) for the faces.. go through pick the best one.. if you're lucky you got the eyes and face in one go... if not you may need to choose the best face.. send back to inpaint again.. select just the eyes.. and rerun a new batch (changing it to only masked and the settings described above for eyes.)
Finally when you get it all together send to extras:
Resize to 1.5-2
Upscale 1= Nearest
Upscale 2= R-ESERGAN 2x or 4x
But google or get yourself these:
(Install these into the proper directory: A1111-Web-UI-Autoinstaller\stable-diffusion-webui\models\ESRGAN and reload a1111.)
Upscaler 2 is what will get you the results you want. You can also drag the upscaler 2 visibility to control the amount of effect each puts on the finished result. (I recommend turning it up 1 but YMMV.)
Ramacri / Lollypop / & Fatality Comix are neck and neck for the best output!
They are all different. One is sharpest, One is more subdued, and one is like a sharp HD.
Each are good for any type of comic / illustration / cell shading / anime.
NMKD_Super is more for semi-realistic to real images and good for scenery. Tends to run sharp so you may have to turn it down a bit.
Each of these is unique and so is their outputs if you want to compare simply change the pull down and run off the various types and contrast / compare all your the finished results.
For the more advanced upscale: Get yourself
(click the link for a basic tutorial on how to get it and how to use it.)
Good Luck & Have Fun!
트리거 단어
comic style
illustrated
realistic
2D
fantasy art
photorealistic
line art
sketch
concept art
character design
concept sheet
colored line art
SHA256
76E38694AEC32A966205735636163D1C90EE9739DFBF0E305C50E9A67216BBE8
ModelTrends.ai 모델 ID
#7293
콘텐츠 신고
예시 작품
Civitai에서 이 작품들을 만든 사람들이 공유한 프롬프트와 설정입니다. 작품을 선택하면 어떻게 만들어졌는지 볼 수 있습니다.
설정
샘플러
Euler a
스텝
40
가이던스
7.5
시드
4273056375
크기
544x960
프롬프트
female,robot ,female,robot cyborg mech, peach hair, cyberpunk:0.35, <lora:nijiarmor_v2:1.0> <lora:EnvyBeautyMix09:1>, perfect lighting, perfect shading, detailed, intricate, (perfect body), beautiful face, flowing hair, ((full torso)), photorealistic:1.35, mature adult:1.4,
네거티브 프롬프트
NSFW,deformed,large breasts,missing limbs,amputated,pants,shorts,cat ears,bad anatomy, naked, no clothes,disfigured, poorly drawn face, mutation, mutated,ugly, disgusting, blurry, watermark, watermarked, oversaturated, obese, doubled face,b&w, black and white, sepia, nude, freckles, no masks,duplicate image, blur, paintings, sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, monochrome, grayscale, bad anatomy,(fat:1.2),facing away, looking away,tilted head,lowres,bad anatomy,bad hands, text, error, missing fingers,extra digit, fewer digits, cropped, worst quality, low quality, normal quality,jpegartifacts,signature, watermark, username,blurry,bad feet,cropped,worst quality,low quality,normal quality,jpeg (artifacts:1.2),signature,watermark,
설정
샘플러
DPM++ SDE Karras
스텝
80
가이던스
7
시드
4038935194
크기
800x1200
프롬프트
(Line Art:1.2), (dark shot:1.4), full body, 80mm, epic realistic, (painting of a geisha) with european features (walking through a japanese pine forest), by range murata, a big ((red sun in the background)), (beautiful cloudy sky), stunning, matted, paul gauguin, van gogh, art by greg rutkowski and artgerm, soft cinematic light, adobe lightroom, photolab, hdr, intricate, highly detailed, (depth of field:1.4), (dark shot:1.22), neutral colors, (hdr:1.4), (muted colors:1.4), (intricate), (artstation:1.2), hyperdetailed, dramatic, intricate details, (technicolor:0.9), (rutkowski:0.8), cinematic, detailed, soft light, sharp, exposure blend, medium shot, bokeh, (hdr:1.4), high contrast, (cinematic, teal and orange:0.85), (realistic and beautiful fabric:0.75), (muted colors, dim colors, soothing tones:1.3), low saturation, (hyperdetailed:1.2), (noir:0.3), soft light, sharp, exposure blend, medium shot, bokeh, (hdr:1.4), high contrast, (cinematic, teal and orange:0.85), (muted colors, dim colors, soothing tones:1.3), low saturation, (hyperdetailed:1.2), (noir:0.4), (intricate details:1.12), hdr, (intricate details, hyperdetailed:1.25), asian face:0.66, (mature adult:1.35), <lora:more_details:0.33>, (photorealistic:1.5)
네거티브 프롬프트
neon, neon, 3d, cartoon, anime, sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, girl, loli, young, large breasts, red eyes, muscular, over saturated, over saturated, over exposed, (bad anatomy), (bad proportions), ((deformed limbs)), ((broken limbs)), ((bad hands)), ((broken hands)), ((ugly hands)), ((deformed hands)), ((missing hands)), (((extra hands))), (((extra arms))), ((backwards hands)), ((revered hands)), ((bad fingers)), ((broken fingers)), ((ugly fingers)), ((deformed fingers)), (((missing fingers))), (((extra fingers))), (((extra digits))), (((missing digits))), EasyNegative, ((anime_badhandv4)), ((bad-hands-5)), (rear view, back view), (BadDream, UnrealisticDream), EasyNegative, (young:1.35),
설정
샘플러
DPM++ SDE Karras
스텝
99
가이던스
7
시드
1653805062
크기
2240x3328
프롬프트
((full body)), (([best quality, absurdres, beautiful detailed_1.2])), (an extremely delicate and beautiful:1.4), detailed closeup (to be defined), upper body, (extremely detailed), ((masterpiece, highres)), beautiful detailed eyes, (ulzzang-6500:0.55), perfectly detailed, ultra detailed, (pureerosface_v1:0.6), (krface1:0.5), <lora:LightningvfxCreateMore_v1:0.5>, <lora:lightAndShadow_v10:0.2>, ((dark ages gothic fantasy), glowing eyes), (a painting of a woman with a sword and wings in style of luis royo), pale skin, standing above the viewer on a rock, power pose, looking at viewer, flowing with dark power, magical girl, mage, wizard, spell, boss Villain, (serious), aura, dark aura, stockings, (blue purple, energy), skeletal armor:0.3, (DarkFantasy), (long silver flowing hair), eye reflection, pure white eyes, perfect face, perfect body, realistic skin texture, highly detailed face, <lora:fantasyV1.1:0.2>, <lora:add_detail:0.25>, centered, (art by Ken Kelly), (photorealistic:1.5)
OR
(portrait), (lightning in background), (photorealistic:1.5), (Oil Painting), (Fantasy Poster), intricate, detailed, perfect lighting, highest quality, good shading, good highlights, perfect composition, good composition, award winning, masterpiece,
네거티브 프롬프트
(comic style), (([worst quality, low quality_1.4])), ([loli, normal quality, lowres_1.2]), (([By bad artist -neg, easynegative, bad-hands-5_1.3])), hetero, blush, (extra arms, extra appendages, missing arms, deformed arms, broken arms, extra hands, missing hands, deformed hands, broken hands, extra fingers, extra digits, missing fingers, deformed fingers, broken fingers:1.5), (words, text, logo, title, brand, font, signature:1.6), bad anatomy, bad proportions, (under-exposed), (detached wings, missing wings),
설정
샘플러
DPM++ 2M Karras
스텝
30
가이던스
6
시드
1206222124
크기
512x768
프롬프트
illustration, cartoon, dark colors, soothing tones, epic realistic, diablo 4 wallpaper, (dark background:1.5)
네거티브 프롬프트
EasyNegative,
설정
샘플러
DPM++ SDE Karras
스텝
99
가이던스
7
시드
2796906338
크기
2240x3328
프롬프트
1girl water yushushui, solo,light_blue_hair,liquid hair, long hair,floating hair, full body, standing,sundress, liquid clothes, iridescent, water,waves, tsunami,tide,sea,water dress,fantasy, high contrast, ink strokes, explosions, over exposure, purple and red tone impression , abstract, water bender, warrior, dynamic pose, action pose, serious, intense, focused, superhero, ((watercolor painting by John Berkey and Jeremy Mann )) brush strokes, negative space, perfect lighting, perfect shading, (stunning, beautiful, gorgeous), 8k, wallpaper, masterpiece, <lora:LiquidClothesV1:1> <lora:yushui:0.35>, (photorealistic:1.5), (mature adult:1.3), centered, (beautiful face, beautiful hair)
네거티브 프롬프트
(worst quality, low quality, normal quality, lowres:1.6), bad anatomy, bad proportions, bad hands, normal quality, ((monochrome)), ((grayscale)), EasyNegative, (((anime_badhandv4, bad-hands-5))), (deformed hands, broken hands, inverted hands, missing hands, extra hands, deformed fingers, broken fingers, missing fingers, extra fingers:1.5), (((buildings, architecture))), (skinny, thin:1.3),
설정
샘플러
DDIM
스텝
99
가이던스
7
시드
4226608206
크기
2176x3200
프롬프트
(comic style), (line art:1.6), (cowboy shot), close up shot of a beautiful woman, long flowing white hair, pointed ears, intense looking focus, (navy blue cape), (royal silver armor), (gilded armor:0.2), (skeletal armor:0.4), (beautiful formed wings),
(magical energy fields flowing around her), beautiful face, perfect eyes, perfect body, ethereal,
fantasy, medieval, dramatic lighting, powerful pose, (detailed, intricate),
(best quality, award winning, masterpiece), volumetric lighting, subsurface scattering, good composition, cinematic,
line art by [Duccio:Drew Struzan:0.7], <lora:LowRA_v20:0.5>, (mature adult:1.37), (photorealistic:1.4),
네거티브 프롬프트
(Low Quality, Bad Quality, Bad Art, Bad Design, Lowres:1.37), EasyNegative, ng_deepnegative_v1_75t, bad anatomy, bad proportions, bad composition, (deformed hands, broken hand, inverted hands, ugly hands, missing hands, extra hands, deformed fingers, broken fingers, ugly fingers, missing fingers, extra fingers:1.5), (worst quality), ((anime_badhandv4, bad-hands-5, negative_hand-neg)), (gold), (extra long hair:0.3), (black wings), (BadDream, UnrealisticDream),
설정
샘플러
Euler a
스텝
30
가이던스
7
시드
3873838329
크기
512x768
프롬프트
(An intricate forest minitown landscape trapped in a bottle), atmospheric oliva lighting, on the table, 4k UHD, dark vibes, hyper detailed, vibrant colours, epic composition, octane render, sharp focus, high resolution isometric
네거티브 프롬프트
EasyNegative, ((nude, naked,child, child face))), un-detailed skin, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, ugly eyes, (out of frame:1.3), worst quality, low quality, jpeg artifacts, cgi, sketch, cartoon, drawing, (out of frame:1.1), worst quality, low quality, jpeg artifacts, poorly drawn, (((word, words, letter, text, signature, watermark))), (BadDream, UnrealisticDream),
유사한 모델
이미지·영상·텍스트 생성을 위한 AI 모델
marvels4은(는) Stable Diffusion 1.5 패밀리용 베이스 모델으로, 오픈 소스 AI 이미지·영상·텍스트 모델의 읽기 전용 카탈로그인 ModelTrends.ai에 등록되어 있습니다. 다른 Stable Diffusion 1.5 모델과 비교하고, 열기 점수로 트렌드를 확인하고, PirateDiffusion 또는 BitVector에서 열어 사용해 보세요.
Stable Diffusion 1.5 모델 더 보기Stable Diffusion 1.5 베이스 모델 더 보기comicsrealisticfantasysci-firetrobackgroundsgraphic-designartstyles
모델 패밀리별로 보기
Text / LLM 모델
411
Anima 모델
509
Chroma 모델
14
Flux 모델
1,071
Flux 2 / Klein 모델
1,237
MiniMax H3 모델
331
Hunyuan 모델
197
Ideogram 모델
20
Krea2 모델
674
Qwen 모델
17
Qwen2 모델
36
Ltx2 모델
150
Stable Diffusion 1.5 모델
6,465
Stable Diffusion XL 1.0 모델
15,432
Zimage 모델
804
Wan 모델
919

Model
Trends
.ai
© ModelTrends.ai
|
일본에서 제작
|
© 2026
