import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Tongyi-MAI/Z-Image-Turbo", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("danrhern/XUPLX")
prompt = "-"
image = pipe(prompt).images[0]XUPLX_UglyPeopleLoRA
- Prompt
- -
Model description
XUPLX_UglyPeopleLoRA is intended to break up the monotony of ZImageTurbo output by forcing interesting compositions, character designs, camera angles, action and other attributes into the output image.
Use XUPLX_UglyPeopleLoRA with the XUPLX Merge Workflow for ZImageTurbo to merge multiple image generations into a single composition with full control.
https://civitai.com/models/2221102/xuplx-merge-workflow
Trigger words
You should use XUPLX to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 100
Model tree for danrhern/XUPLX
Base model
Tongyi-MAI/Z-Image-Turbo