Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
AI Model Training

Create Your Own AI Model

Train AI to generate stunning photos of yourself in any style or setting

Model Description by Creator

You've been asking me to make Marisa Mamiya ever since I made Marie Mamiya :3 So get a blondie dominatrix!

0.75 - 1 strength of Lora is the best radius (For combining with other LoRAs, I recommend reducing weight).

Clip skip 2

Some necessary tokens for better experience:

Main tokens:
MarisaMamiya, 1girl,
blonde hair, short hair, detailed hair, hairband, blue eyes, jewelry, necklace, cross, choker,

Dress:

black dress, miniskirt, white thighhighs,

Sexy bikini:

micro bikini, white bikini, highleg bikini, frills, underboob

Also you can use another tokens for her body and clothes :3

Main advices for all LoRAs:

I recommend you next prompt order for NAI-based mixes (you can see it in my preview arts):

  1. (high quality:1.2) ("masterpiece" and "8K" kill some concepts. Be careful if you try some complex clothes or concepts.)

    Also put lighting / shadows, intricate details if you need some extra effects. Sometimes it doesn't work if style of anime or game was baked in LoRA or anime checkpoint mixes lost some concepts which exists in vanilla SD 1.5.

  2. Activation word (from lora civitai page, usually character name). Describe with danbooru tags character activity, expressions, camera position.

  3. Hair details, face details, jewelry, crowns, hats, etc.

  4. Clothes and shoes; Or nude.

  5. Body details (large breasts, cleavage). Genitals if you want to generate it.

  6. Background.

Advices for upscaling / fixing:

  • use highres.fix (If you are sure that your prompt is easy for SD); I prefer x4_Fatal_anime_500000_G, animesharp, foolhardy_remacri, siax with 1.5x - 2x upscale. 0.36 denoising and 15-18 Hires fix is enough.

  • Do not use "latent" upscaler because it works worse with denoisning < 0.5 but you don't want so high denoising stength because it changes your image instead of adding details.

  • use extention after detailer for better faces. It is better than inpaint.

  • use SD Upscale / Ultimate SD Upscale script in img2img after highres fix if you want 4K or more resolution with adding details (don't use Extras for it).

  • Use inpaint and sketch for other details;

  • Use Photoshop / Photopea extension for fixing hands, textures and other.

I will be glad to receive feedback from you and a demonstration of your art with my LoRA!

https://tensor.art/u/604375505701151021

Images Generated With This Model

(masterpiece, high quality:1.1), cinematic lighting, extremely detailed, shadow,
MarisaMamiya, 1girl, solo, sitting, on sofa, crossed legs,  full body, from below, dominatrix, 
looking at viewer, scowl, (teeth:1.1),
blonde hair, short hair, detailed hair, hairband, blue eyes, jewelry, necklace, cross, choker,
black dress, see-through, miniskirt, (white thighhighs:1.1), high heels,
large breasts, cleavage, zettai ryouiki, 
luxury mansion, royal room, windows, complex background,
<lora:MarisaMamiya:0.9>
N/A
Hidden For Public Users
(masterpiece, high quality:1.1), cinematic lighting, extremely detailed, shadow, MarisaMamiya, 1girl, solo, sitting, on sofa, crossed legs, full body, from below, dominatrix, looking at viewer, scowl, (teeth:1.1), blonde hair, short hair, detailed hair, hairband, blue eyes, jewelry, necklace, cross, choker, black dress, see-through, miniskirt, (white thighhighs:1.1), high heels, large breasts, cleavage, zettai ryouiki, luxury mansion, royal room, windows, complex background, <lora:MarisaMamiya:0.9>
(masterpiece, high quality:1.1), cinematic lighting, extremely detailed, shadow,
MarisaMamiya, 1girl, solo, hand on hip, hand on own face, full body,
looking at viewer, scowl, (teeth:1.1),
blonde hair, short hair, detailed hair, hairband, blue eyes, jewelry, necklace, cross, choker,
black dress, see-through, miniskirt, (white thighhighs:1.1), high heels,
large breasts, cleavage, zettai ryouiki, 
luxury mansion, royal room, windows, complex background,
<lora:MarisaMamiya:0.9>
N/A
Hidden For Public Users
(masterpiece, high quality:1.1), cinematic lighting, extremely detailed, shadow, MarisaMamiya, 1girl, solo, hand on hip, hand on own face, full body, looking at viewer, scowl, (teeth:1.1), blonde hair, short hair, detailed hair, hairband, blue eyes, jewelry, necklace, cross, choker, black dress, see-through, miniskirt, (white thighhighs:1.1), high heels, large breasts, cleavage, zettai ryouiki, luxury mansion, royal room, windows, complex background, <lora:MarisaMamiya:0.9>
AI Model Training

Create Your Own AI Model

Train AI to generate stunning photos of yourself in any style or setting
(high quality:1.1), cinematic lighting, extremely detailed, shadow,
MarisaMamiya, 1girl, solo, hands on stomach, cowboy shot,
looking at viewer, determined, disdain,
blonde hair, short hair, detailed hair, hairband, blue eyes, jewelry, necklace, cross, choker,
black dress, skirt, white thighhighs,
large breasts, cleavage,
luxury mansion, royal room, windows, complex background,
<lora:MarisaMamiya:1>
N/A
Hidden For Public Users
(high quality:1.1), cinematic lighting, extremely detailed, shadow, MarisaMamiya, 1girl, solo, hands on stomach, cowboy shot, looking at viewer, determined, disdain, blonde hair, short hair, detailed hair, hairband, blue eyes, jewelry, necklace, cross, choker, black dress, skirt, white thighhighs, large breasts, cleavage, luxury mansion, royal room, windows, complex background, <lora:MarisaMamiya:1>
<lora:chunmmfullbody_v1:0.8>, (white shirt:1.1), microskirt, (sheath skirt:1.1), (pantyhose:1.2), corset, chunmomo, 1girl, solo, realistic, looking at viewer, smile, blurry, black eyes, black hair, bangs, long hair, day, blunt bangs, ponytail, soft light, 8K, ultra high resolution, ultra-detailed, photorealistic, an extremely delicate and beautiful, standing caffe, crossed legs, high heels
N/A
Hidden For Public Users
<lora:chunmmfullbody_v1:0.8>, (white shirt:1.1), microskirt, (sheath skirt:1.1), (pantyhose:1.2), corset, chunmomo, 1girl, solo, realistic, looking at viewer, smile, blurry, black eyes, black hair, bangs, long hair, day, blunt bangs, ponytail, soft light, 8K, ultra high resolution, ultra-detailed, photorealistic, an extremely delicate and beautiful, standing caffe, crossed legs, high heels
best quality, (masterpiece:1.5),(ultra-detailed), (high quality:1.3), (high resolution), <lora:sada:0.7>, 1girl,  green eyes, professor_sada, shorts, grey hair,looking at viewer, crop top, perfect eyes, symmetrical eyes, detailed eyes, crossed arms, crossed legs ,(solo:1.1), perfect face, (bright lighting:1.2), detailed eyes, extremely detailed face,sleeveless,  kyokucho,  <lora:kyokucho:0.65>, fcPortrait, orange clothes, collarbone,
N/A
Hidden For Public Users
best quality, (masterpiece:1.5),(ultra-detailed), (high quality:1.3), (high resolution), <lora:sada:0.7>, 1girl, green eyes, professor_sada, shorts, grey hair,looking at viewer, crop top, perfect eyes, symmetrical eyes, detailed eyes, crossed arms, crossed legs ,(solo:1.1), perfect face, (bright lighting:1.2), detailed eyes, extremely detailed face,sleeveless, kyokucho, <lora:kyokucho:0.65>, fcPortrait, orange clothes, collarbone,
professional 3d @canelo as a fighting videogame game demonic character, video game style, masterpiece, best quality, ultra realistic,32k,RAW photo,detail skin, 8k uhd, dslr,high quality, film grain,\nShort and messy hair . dynamic, vibrant, action-packed, detailed character design, reminiscent of fighting video games, black bloody veins growing and intertwining out of the darkness, oozing thick neon rainbow blood, veins growing and pumping blood, vascular networks growing, connecting, explanding, red veins everywhere, zdzislaw beksinski, (vibrant colors:1.1), (Repetition:1.1), (Cross-hatching:1.1), (Infrared:1.2), Rust, Hypercube, ultra detailed, intricate, oil on canvas, ((dry brush, ultra sharp)), (surrealism:1.1), (disturbing:1.1), beksinski style painting, sparks, lensflare, rim lighting, backlighting, RTX, Post Processing, satanic cross, man body, muscular, venom costum . octane render, highly detailed, volumetric, dramatic lighting
N/A
Hidden For Public Users
professional 3d @canelo as a fighting videogame game demonic character, video game style, masterpiece, best quality, ultra realistic,32k,RAW photo,detail skin, 8k uhd, dslr,high quality, film grain,\nShort and messy hair . dynamic, vibrant, action-packed, detailed character design, reminiscent of fighting video games, black bloody veins growing and intertwining out of the darkness, oozing thick neon rainbow blood, veins growing and pumping blood, vascular networks growing, connecting, explanding, red veins everywhere, zdzislaw beksinski, (vibrant colors:1.1), (Repetition:1.1), (Cross-hatching:1.1), (Infrared:1.2), Rust, Hypercube, ultra detailed, intricate, oil on canvas, ((dry brush, ultra sharp)), (surrealism:1.1), (disturbing:1.1), beksinski style painting, sparks, lensflare, rim lighting, backlighting, RTX, Post Processing, satanic cross, man body, muscular, venom costum . octane render, highly detailed, volumetric, dramatic lighting
(masterpiece, high quality:1.1), cinematic lighting, extremely detailed,
MarikaMamiya, walking, full body,
looking at viewer, determined,
green hair, long hair, hair bow, brown eyes, necklace, choker,
(sleeveless short dress, miniskirt:1.1),  center opening, criss-cross halter, bra, detached sleeves, (white thighhighs:1.1), high heels,
large breasts, cleavage,
outdoors, luxury mansion garden, flower field,
<lora:MarikaMamiya:0.9>
N/A
Hidden For Public Users
(masterpiece, high quality:1.1), cinematic lighting, extremely detailed, MarikaMamiya, walking, full body, looking at viewer, determined, green hair, long hair, hair bow, brown eyes, necklace, choker, (sleeveless short dress, miniskirt:1.1), center opening, criss-cross halter, bra, detached sleeves, (white thighhighs:1.1), high heels, large breasts, cleavage, outdoors, luxury mansion garden, flower field, <lora:MarikaMamiya:0.9>
Cthulhu, lovecraft cthulhu, lovecraftian style, cult of Cthulhu, gradient color, jungle, antichrist cross, Cross of Saint Peter, dynamic pose, (digital illustration, Duy Huynh), Jackson Pollock (masterpiece, best quality, beautiful and aesthetic:1.2), cinematic, masterpiece, best quality, detailed, highest quality, ultra detailed, highres, cinematic light, splendid and colorful, out of focus, RAW photograph, art portrait, high contrast, colorful, highest details, neon color, red bloody veins growing and intertwining out of the darkness, oozing thick red blood, veins growing and pumping blood, vascular networks growing, connecting, expanding, red veins everywhere, zdzislaw beksinski, a mind flayer, (Muted colors:1.1), (Repetition:1.1), (Cross-hatching:1.1), (Infrared:1.2), Rust, Sphere, ultra detailed, intricate, oil on canvas, ((dry brush, ultra sharp)), (surrealism:1.1), (disturbing:1.1), beksinski style painting, sparks, lens flare, rim lighting, backlighting, Bracelet, RTX, Post Processing, satanic cross, (masterpiece, detailed, highres:1.2), zdzislaw beksinski, Giger style, beksinski style, satan cross, inverted cross, satanism, Post-apocalypse, futuristic, bright neon clouds, best quality, high resolution, alien, giger, viscera, post, peeled flesh, broken creature, a dangerous looking sprinkled robot bright neon blood on top of a table with a alien head, high contrast, sharp purple neon, in the style of giger in the hole, deep contrast, hyperrealism, hyper realistic color photo, realistic photography, ultra realistic, biomechanical, biomechanism, ((hnsrdlf style)), detailed reflections, dark atmosphere, gothic art, futuristic, realistic blood, realistic reflections, RTX graphic, HDR, ultra detailed, real bloodied photo, award winning glamour photograph, photorealistic
N/A
Hidden For Public Users
Cthulhu, lovecraft cthulhu, lovecraftian style, cult of Cthulhu, gradient color, jungle, antichrist cross, Cross of Saint Peter, dynamic pose, (digital illustration, Duy Huynh), Jackson Pollock (masterpiece, best quality, beautiful and aesthetic:1.2), cinematic, masterpiece, best quality, detailed, highest quality, ultra detailed, highres, cinematic light, splendid and colorful, out of focus, RAW photograph, art portrait, high contrast, colorful, highest details, neon color, red bloody veins growing and intertwining out of the darkness, oozing thick red blood, veins growing and pumping blood, vascular networks growing, connecting, expanding, red veins everywhere, zdzislaw beksinski, a mind flayer, (Muted colors:1.1), (Repetition:1.1), (Cross-hatching:1.1), (Infrared:1.2), Rust, Sphere, ultra detailed, intricate, oil on canvas, ((dry brush, ultra sharp)), (surrealism:1.1), (disturbing:1.1), beksinski style painting, sparks, lens flare, rim lighting, backlighting, Bracelet, RTX, Post Processing, satanic cross, (masterpiece, detailed, highres:1.2), zdzislaw beksinski, Giger style, beksinski style, satan cross, inverted cross, satanism, Post-apocalypse, futuristic, bright neon clouds, best quality, high resolution, alien, giger, viscera, post, peeled flesh, broken creature, a dangerous looking sprinkled robot bright neon blood on top of a table with a alien head, high contrast, sharp purple neon, in the style of giger in the hole, deep contrast, hyperrealism, hyper realistic color photo, realistic photography, ultra realistic, biomechanical, biomechanism, ((hnsrdlf style)), detailed reflections, dark atmosphere, gothic art, futuristic, realistic blood, realistic reflections, RTX graphic, HDR, ultra detailed, real bloodied photo, award winning glamour photograph, photorealistic
masterpiece, best quality, highly detailed, 1girl, (church, praying:1.5), <lora:Tsukihime_Noel_Aizome_v2:0.7>, noel_nunveil, (nun, habit:1.1), black veil, crowds of worshippers:1.5), long dress, knee boots, cross-laced boots, short hair, kneeling, cross necklace, side-swept bangs, brown hair, brown eyes, hair between eyes,
N/A
Hidden For Public Users
masterpiece, best quality, highly detailed, 1girl, (church, praying:1.5), <lora:Tsukihime_Noel_Aizome_v2:0.7>, noel_nunveil, (nun, habit:1.1), black veil, crowds of worshippers:1.5), long dress, knee boots, cross-laced boots, short hair, kneeling, cross necklace, side-swept bangs, brown hair, brown eyes, hair between eyes,

Train Models

Train AI Models On Your Own Pictures

You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.

Generate AI Images. Simple and Easy

AIEasyPic is the #1 AI image generator. Generate images with simple prompts, swap faces, train models to reimagine yourself, and more.