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/Sainker_Illustrious")
prompt = "masterpiece, best quality, watercolor pencil \\(medium\\), no lineart,"
image = pipe(prompt).images[0]Sainker Style - Illustrious
- Prompt
- masterpiece, best quality, watercolor pencil \(medium\), no lineart,
- 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, watercolor pencil \(medium\), no lineart,
- 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, watercolor pencil \(medium\), no lineart,
- 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
Pretty strong style out of the box. So no need to use the artist tag (but you can if you want!). I used the tag 'shiny skin' to get closer to the original style.
Trigger: saiker,
Extra triggers for style: hatching (texture), | watercolor pencil (medium), | no lineart,
Artist trigger: sainker, (yes I made a mistake in the trigger!)
Advised strength: 0.6 - 1.0
Trigger words
You should use saiker to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- -
Model tree for Ava2000/Sainker_Illustrious
Base model
KBlueLeaf/kohaku-xl-beta5 Quantized
calcuis/illustrious