artstation, best quality, masterpiece, ultra detailed illustration, face portrait, <lora:Szayelaporro2:0.7>,  1man, young, slim, ((clean shaven)), Szayelaporro, pink hair, yellow eyes, thin lips, handsome attractive adult man, tall, slim, white glasses, solo, white turtleneck, handsome, highres
rtstation, best quality, masterpiece, ultra detailed illustration, face portrait, hands in pockets, <lora:Szayelaporro2:0.6>,  1man, slim, ((clean shaven)), Szayelaporro, pink hair, yellow eyes, thin lips, handsome attractive adult man, tall, slim, glasses, solo, white turtleneck, black stripes, white hakama, handsome,  (perfect composition:1.4), deviantart hd, artstation hd, concept art, detailed face and body, detailed hands, backlight, 12k ultrarealistic, highres,  cinematic lighting, night, darkness desert, sand, sandy potholes, crescent, half moon, demilune, 8k
rtstation, best quality, masterpiece, ultra detailed illustration, <lora:Szayelaporro2:0.7>,  1man, slender, ((clean shaven)), Szayelaporro, pink hair, yellow eyes, thin lips, handsome attractive adult man, tall, glasses, solo, white turtleneck, white hakama, handsome, (perfect composition:1.4), deviantart hd, artstation hd, concept art, detailed face and body, detailed hands, backlight, 12k ultrarealistic, smiling,  wet, damp, wetness, puddles, raindrops, drops, splashes, water, wet pavement, reflections, neon lights, night, evening, darkness, streetlights, lampposts, buildings, city, urban, downtown, town, houses, windows, lights, bright, vibrant, colorful, highres
Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
* This model is available for use and will generate similar character to the ones seen in the images.

Model Description by Creator

This is the model uploaded by fan for fans.

I didn't focus on the Kubo Tite style. I didn't use fanart for training, other than a couple of my own drawings to vary the style.

It should work normally with NAI based models. I personally tried it with AbyssOrangeMix2 and Anything v4.5. It's ok.

Important notes:

  • Here are five working versions. They are all different and all can produce different but acceptable result.

  • I would recomend you to use Anything v.4.5 VAE for generation.

  • For the canonical clothing style generations: it's better using v4 and v5 loras, using triggers turleneck ,hakama, gloves, glasses. I would recommend you to use v5 or v1 for generation the pose and v4 for inpainting.

  • And yellow eyes, glasses, pink hair - for the face.

  • I don't recommend you to use Hires. fix if you want to keep the canon face. It's better to send it to inpaint and to use the mask for the face.

  • Use higher weight and resolution inpainting face.

  • Try to use Keanu Reaves haircutor Keanu Reaves face shape in your prompt. I didn't use it for the training process it's just working for Szayelaporro in stable diffusion itself.

  • You can also try to save this as a style:

    best quality, masterpiece, original art, full body, 1man, solo, (adult:1.4), (slim), ((skinny)), (((slender))), tall, sexy, handsome, attractive, (white kilt:1.4), (white turtleneck), (white leggings), (white clothes), (((adult face))), (((manly face))), ((long face)), (((Keanu Reeves haircut))), hair over one eye, (((pink-haired))), (((smiling))), (((yellow eyes))), (((white glasses))), handsome symmetrical face, posing sexy, perfect face, 8k

    Negative: formal suit, beard, unshaven, (worst quality, low quality:1.3), (depth of field, blurry:1.2), (greyscale, monochrome:1.1), muscular, low quality, сhildish, female, female face, girlish face, girl, young, blur, bad anatomy, breasts, bad hands, mutated hand, text, error, missing fingers, extra digit, fewer digits, username, blurry, artist name, out of focus, glowing eyes, bad proportions, (((multiple legs))), (((multiple arms))), pointy ears, ponytail, (tan, muscular, loli, petite, child, infant, toddlers, chibi, sd character:1.1), multiple view, multiple characters, reference sheet

P.S: I'm using xformers so your results with the same prompt can be slightly different.

Images Generated With This Model

Loading...

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.
Train Your Own Model

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.