mksks style, 1boy, library, scenery, (multiple arms, crossed arms:1.4), lots of skull on ground, from side, gold ornament, (scar on face, torn stuffed toy, weaving machine:1.1), BREAK multicolored eyes, best quality, detailed background, masterpiece, oil painting \(medium\), tkstyle <lora:tkstyle_2:0.8>
1girl, long hair, messy hair, fleeing, running, bloodshot eyes, intricate lace dress, black sash, tokyo metro, on tank, underground station, broken lamp, (clenched teeth, aura:1.3), scenery, best quality, masterpiece, oil painting \(medium\), tkstyle <lora:tkstyle_2:0.8>
1girl, lying, sleeping, on bed, from above, smile, closed eyes, asymmetrical hair, hair extensions, metallic pants, thick thighs, gloves, glowing eyes, scenery, melancholic, depression, ferris wheel, decay towers, falling raindrop, outdoors, painting \(medium\), tkstyle, best quality, vivid coloring, masterpiece <lora:tkstyle:0.8>
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

Style by artist Tobias Kwan's illustrations.

His paintings have a distinctive style that is both decadent and noble, often depicting eerie humanoid creatures and dark fantasy animals. (His work has been featured in the album artwork of the V-kei band the GazettE.)

This LoRA is very prone to finger problems. Sorry, it is hard to handle, so don't expect perfection.

Trigger word: tkstyle

Variation keywords: oil painting \(medium\), painting \(medium\), traditional media, abstract, dark, horror \(theme\), monster etc.

Recommended weight: 0.5-1

Sampler:

Euler a - Smooth details and stable rendering.

DPM++ SDE Karras - Impasto-like and rough texture in details.

DPM++ 2M Karras - Probably not a good match, I think it tends to mix blur and noise in the details.

Hires Fix:

In testing with 4x-UltraSharp, Denoising strength 0.3-0.5 seems good.

Translated by DeepL

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.