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/Kujou_Kiyo_Illustrious")
prompt = "masterpiece, best quality, eyelashes, four fingers and a thumb,"
image = pipe(prompt).images[0]Kujou Kiyo Style - Illustrious
- Prompt
- masterpiece, best quality, eyelashes, four fingers and a thumb,
- 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, monochrome, greyscale, grin,
- Prompt
- masterpiece, best quality, eyelashes, four fingers and a thumb,
- 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, monochrome, greyscale, grin,
Model description
The style of Kujou Kiyo
I made this lora to try and reproduce the style of Kujou Kiyo. You can use the artist tag with this lora, but in my opinion it doesn't add much. Fingers have always been a problem with this lora.
For my positives I use: masterpiece, best quality, eyelashes, four fingers and a thumb,
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: qjukiyo,
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 qjukiyo to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 19
Model tree for Ava2000/Kujou_Kiyo_Illustrious
Base model
KBlueLeaf/kohaku-xl-beta5