metadata
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- output:
url: images/00061-368465413.png
text: >-
masterpiece, best quality, traditional media, (jaggy lines, sketch),
watercolor pencil \(medium\), monochrome,
parameters:
negative_prompt: >-
text, long body, lowres, cropped, lowres, jpeg artifacts, (artist name,
watermark, username, english text, signature:1.5), simple background,
conjoined, out of frame, out of frame, censored, bar censor,
- output:
url: images/00063-2572820958.png
text: >-
masterpiece, best quality, traditional media, (jaggy lines, sketch),
watercolor pencil \(medium\), monochrome,
parameters:
negative_prompt: >-
text, long body, lowres, cropped, lowres, jpeg artifacts, (artist name,
watermark, username, english text, signature:1.5), simple background,
conjoined, out of frame, out of frame, censored, bar censor,
base_model: calcuis/illustrious
instance_prompt: b3rm00l1
Bermooli Style - Illustrious
- Prompt
- masterpiece, best quality, traditional media, (jaggy lines, sketch), watercolor pencil \(medium\), monochrome,
- Negative Prompt
- text, long body, lowres, cropped, lowres, jpeg artifacts, (artist name, watermark, username, english text, signature:1.5), simple background, conjoined, out of frame, out of frame, censored, bar censor,
- Prompt
- masterpiece, best quality, traditional media, (jaggy lines, sketch), watercolor pencil \(medium\), monochrome,
- Negative Prompt
- text, long body, lowres, cropped, lowres, jpeg artifacts, (artist name, watermark, username, english text, signature:1.5), simple background, conjoined, out of frame, out of frame, censored, bar censor,
Model description
This is the style of Bermooli. Which I found on Twitter. The dataset was made up from mostly art featuring the same characters (Princess Bubblegum and Marceline). It is a very cute drawing style, but might be limited in scope because of it's focus on these 2 characters. The characters tags weren't added in the dataset!
Trigger: b3rm00l1,
Extra triggers for style: masterpiece, best quality, traditional media, (jaggy lines, sketch), watercolor pencil (medium), monochrome,
Extra tags: greyscale,
Advised strength: 0.6 - 1.0
Trigger words
You should use b3rm00l1 to trigger the image generation.
Download model
Download them in the Files & versions tab.