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/Mikoyan_Illustrious")
prompt = "masterpiece, best quality,"
image = pipe(prompt).images[0]Mikoyan Style - Illustrious
- Prompt
- masterpiece, best quality,
- 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,
- 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 Mikoyan. Works the best in combination with the artist tag, but on itself it is also strong enough.
Trigger: mikoyanstyle,
Extra triggers for style: masterpiece, best quality,
Atist tags: mikoyan,
Advised strength: 0.6 - 1.0
Trigger words
You should use mikoyanstyle to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 14
Model tree for Ava2000/Mikoyan_Illustrious
Base model
KBlueLeaf/kohaku-xl-beta5 Quantized
calcuis/illustrious