Hi, there are 3 versions of this lora:

- V1 - 9B: It's better on more doodle style, more colorful
- V2 - 9B: It's better on scribble style, less detail, more wonky
- V1 - 4B: Flux.2 Klein 4B version of the lora


Prompt: Redraw this image in the most clumsy, scribbly, and utterly pathetic way possible. Use a white background, and make it look like it was drawn by a terrible artist. It should be vaguely similar but also not really, kind of matching but also off in a confusing, awkward way, with that low-quality pixel-by-pixel feel that really emphasizes how ridiculously bad it is.


Another version of the prompt, it's restricts the usage of the white color and makes it more colorful(you can play with the prompt slightly based on your goal):

Redraw the attached image in the most clumsy, scribbly, and utterly pathetic way possible. Use a utterly pathetic background, and make it look like it was drawn by a terrible artist. It should be vaguely similar but also not really, kind of matching but also off in a confusing, awkward way, with that low-quality pixel-by-pixel feel that really emphasizes how ridiculously bad it is. You cant use white color more than 5% of the image.

Trained on AI Toolkit by Ostris