import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("calcuis/illustrious", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Ava2000/Maniacpaint_Illustrious")
prompt = "masterpiece, best quality, traditional media, jaggy lines, sketch,"
image = pipe(prompt).images[0]Maniacpaint Style - Illustrious
- Prompt
- masterpiece, best quality, traditional media, jaggy lines, sketch,
- Negative Prompt
- text, long body, lowres, cropped, lowres, jpeg artifacts, (signature, artist name, watermark, username, english text, signature:1.4), simple background, conjoined, out of frame, out of frame, censored, bar censor,
Model description
The style of Maniacpaint.
I made this lora to try and reproduce the style of Maniacpaint. The style is know for it's sketches, so you might have to up the strength of the 'sketch' tag or use other prompts to get a stronger effect.
For my positives I use: masterpiece, best quality, traditional media, jaggy lines, sketch,
And for my negatives: text, long body, lowres, cropped, lowres, jpeg artifacts, (signature, artist name, watermark, username, english text, signature:1.4), simple background, conjoined, out of frame, out of frame, censored, bar censor,
Trigger: ma1n1cpa1nt,
Advised strength: 0.6-1.0
I also use reForge with Adetailer (only the face model), CD Turner, FreeU and SelfAttentionGuidance (only for Illustrious), but they are not a must.
Trigger words
You should use ma1n1cpa1nt to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 26
Model tree for Ava2000/Maniacpaint_Illustrious
Base model
KBlueLeaf/kohaku-xl-beta5