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/PHM_v3_lora")
prompt = "(masterpiece, best quality:1.2), amazing quality, very aesthetic, 32k, absurdres, newest, scenery, "
image = pipe(prompt).images[0]PHM_v3_lora
- Prompt
- (masterpiece, best quality:1.2), amazing quality, very aesthetic, 32k, absurdres, newest, scenery,
- Negative Prompt
- worst aesthetic, (worst quality, low quality, bad quality:1.4), lowres, worst detail, scan artifacts, jpeg artifacts, lossy-lossless, aliasing, downscaled, ai-generated, old,
Trigger words
You should use <lora:PHM_style_IL_v3.3:1.0> to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 1,450
Model tree for Shero448/PHM_v3_lora
Base model
dhead/wai-nsfw-illustrious-sdxl-v140-sdxl