Sign In

Schematics

828
6.3k
182
Verified:
SafeTensor
Type
LoRA
Stats
4,490
Reviews
Published
Sep 24, 2023
Base Model
SDXL 1.0
Usage Tips
Clip Skip: 1
Trigger Words
xk3mt1ks
Hash
AutoV2
3F5A42021E

Hi again and welcome to Schematics!


"Schematics" is a very personal LORA where I aim to create an overall style but oriented mostly for certain style aesthetics so it can be used for characters, objects, landscapes, etc. This time you get "wired" and "schemes" effect as aesthetics.


"Schematics" aims to create globalized creations but with wired and schemes graphic aesthetics. This LORA is extremely good for sci-fi, robots, mechas, surreal scenes, certain graphic art, posters etc.

Main token is xk3mt1ks and class is style so you can use xk3mt1ks style or just xk3mt1ks. I recommend this time the first case.

Important: This LORA has subtokens and those are "over black background" and "over white background" and depending on how you use them you get one effect or another (this was a fun experiment to play)

How to use this LORA?

*************************

You can refer to the sample images I upload in the post but:

- For characters a portrait of "concept" in the style of xk3mt1ks

- For landscape and objects xk3mt1ks style concept or a "concept" in the style of xk3mt1ks

Which are the best values?
*******************************

- You can go from 0.7/0.8 onwards till 1 and 1 onwards for a more "xk3mt1ks style".



Which models are good for this LORA?
********************************************

- Tested on 5 different models except on (as always) Realistic Vision but I'd recommend Colorful, RevAnimated, Dreamshaper... if you use anime models like Cardos mind that the style will adapt towards anime with all it's lineart area, so be careful.

This LORA is GOOD for:
******************************

- Detailed sci-fi scenes
- Detailed portraits with aesthetics of wires
- Surreal scenes
- Dynamic colors
- Graphic design style for your creations.

- Globalized creations (such as really anything you want). Just remember what happens
with anime models.


This LORA is NOT designed for:
***********************************

- Realistic things (maybe) since it's trained on certain drawings and illustrations. Should be difficul to guide it to a realistic basis.

IMPORTANT!

I wrote an article here and it's like my finetunning diary for the ones interested with releases upcoming, trainings done, exclusive patreon models previews, personal thoughts, etc. So if you want to see what I'm planning or what I'm into, feel free to take a look.

As always thanks to everyone reviewing, giving feedback , commenting and supportin us in Patreon. Keep supporting us so we can keep creating and delivering quality content.

David.