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/Rezodwel_Illustrious")
prompt = "masterpiece, best quality, flat color, "
image = pipe(prompt).images[0]Rezodwel Style - Illustrious
- Prompt
- masterpiece, best quality, flat color,
- 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
I baked in the artist name/watermark by accident (I forgot to add the tags for 'artist name' and 'watermark'). But the final result is still good so I decided to upload it. Will probably fix it later or when moving over to Anima. Use the artist tag if you want to get the most out of it ('rezodwel').
Trigger: r3z0dw31,
Extra triggers for style: flat color,
Advised strength: 0.6 - 1.0
Trigger words
You should use r3z0dw31 to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 6
Model tree for Ava2000/Rezodwel_Illustrious
Base model
KBlueLeaf/kohaku-xl-beta5 Quantized
calcuis/illustrious