import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("dhead/wai-nsfw-illustrious-sdxl-v140-sdxl", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Shero448/LMB_style_lora")
prompt = "(masterpiece, best quality:1.2), amazing quality, very aesthetic, 32k, absurdres, extremely beautiful, newest, scenery, extra details, (sharp detailed:1.2), "
image = pipe(prompt).images[0]LMB_style_lora
- Prompt
- (masterpiece, best quality:1.2), amazing quality, very aesthetic, 32k, absurdres, extremely beautiful, newest, scenery, extra details, (sharp detailed:1.2),
- Negative Prompt
- eyewear_on_head ,(lowres, bad quality, low quality, worst quality:1.2), worst detail, jpeg artifacts, cropped, resolution mismatch, resized, bad source,
Trigger words
You should use lmb to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 4
Model tree for Shero448/LMB_style_lora
Base model
dhead/wai-nsfw-illustrious-sdxl-v140-sdxl