import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("John6666/prefect-illustrious-xl-v10-sdxl", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Shero448/zhuyuan-ilus")
prompt = "masterpiece, best quality, <break> solo, 1girl, zhu yuan, expressionless, looking at viewer, standing, holding gun, handgun, hand up, hand on own hip, ponytail, red eyes, police uniform, blue jacket, cropped jacket, open jacket, long sleeves, black gloves, black vest, white shirt, collared shirt, checkered necktie, black pants, tight pants, high-waist pants, outdoors, blue sky, cloud, city"
image = pipe(prompt).images[0]zhuyuan-ilus
- Prompt
- masterpiece, best quality, <break> solo, 1girl, zhu yuan, expressionless, looking at viewer, standing, holding gun, handgun, hand up, hand on own hip, ponytail, red eyes, police uniform, blue jacket, cropped jacket, open jacket, long sleeves, black gloves, black vest, white shirt, collared shirt, checkered necktie, black pants, tight pants, high-waist pants, outdoors, blue sky, cloud, city
- Negative Prompt
- worst quality, low quality, jpeg artifacts, multiple views, 4koma, bad anatomy, bad hands, text
Trigger words
You should use zhu yuan to trigger the image generation.
You should use ponytail to trigger the image generation.
You should use red eyes to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 3
Model tree for Shero448/zhuyuan-ilus
Base model
KBlueLeaf/kohaku-xl-beta5 Finetuned
John6666/prefect-illustrious-xl-v10-sdxl