All Images Here Are Generated By AI.

All Models

>

Ginko | Mushishi

(masterpiece, top quality, best quality, official art, detailed:1.2),<lora:ginko-21:0.7>, ginko_soul3142, solo, 1boy, green eyes, white hair, male focus, hair over one eye, cigarette, smoking
(masterpiece, top quality, best quality, official art, detailed:1.2),<lora:ginko-21:0.7>, ginko_soul3142, solo, 1boy, green eyes, white hair, male focus, hair over one eye, cigarette, smoking
(masterpiece, top quality, best quality, official art, detailed:1.2),<lora:ginko-21:0.7>, ginko_soul3142, solo, 1boy, white hair, white shirt, flower, outdoors, sky, cloud, night, bug, butterfly, star (sky), night sky, scenery, starry sky, field, shooting star
(masterpiece, top quality, best quality, official art, detailed:1.2),<lora:ginko-21:0.7>, ginko_soul3142, solo, 1boy, white hair, white shirt, flower, outdoors, sky, cloud, night, bug, butterfly, star (sky), night sky, scenery, starry sky, field, shooting star

Generate AI Images. Simple and Easy

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

Model Description by Creator

Character Lora of Ginko from the anime Mushishi

with its soft nature inspired muted watercolor-y artstyle. One of my all time favourite anime.

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

If you want to, you can support me on Patreon or Buy me Coffee.

I've also made Characters from Witcher Universe - soul3142's Guide to the Witcher Universe, plus some other game/vn characters also.


Main Trigger Word - ginko_soul3142 , check examples for other ones.


Recommendations :-

  1. Highres Fix - must, if you are getting blurry and ugly images

    My upscale method: txt2img 512x768 -> send to img2img -> controlnet tile upscale, tile diffusion 2x scale with 4xUltrasharp upscaler and tiled vae

  2. Weight: 0.6 - 0.8

  3. Clip Skip: 2

  4. Steps: 25-30

  5. CFG: 7-8

  6. Denoising - Don't go too high, it can alter a lot of details

I use 0.7 weight, 25 steps, Euler a, Clip skip 2 in nearly all my examples with almost same, simple +ve/-ve prompts regardless of checkpoint for my own consistency purposes.

There are imperfections here & there, which i usually leave it in as is, (i never do any inpainting in examples), most of which like hands can be fixed with better prompting, negative embeddings while other like weapons are just bad majority of the time no matter the model as of today.

Some LoRA's are flexible with any clothing, some are not (usually character's with single costume) so keep these things in mind.

This is an unofficial fanmade LoRA, not intended for any commercial purpose and use. All characters and IP rights are owned by their respective creators and owners. I do not own rights to any of these characters.

Try Full Demo
Quick Generate
Image quality might not be as good as what you can achieve with our full generation tool.
Placeholder
Choose A Style, Type What You Want In The Image And Click Generate
Placeholder
Choose A Style, Type What You Want In The Image 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.
Train Your Own Model

Images Generated With This Model

Loading...

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.