import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Benevolent/VeryBadImageNegative")
prompt = "UNICODE\u0000\u0000 \u0000r\u0000e\u0000f\u0000a\u0000m\u0000,\u0000 \u0000<\u0000l\u0000o\u0000r\u0000a\u0000:\u0000f\u0000a\u0000m\u0000-\u0000l\u0000o\u0000r\u0000a\u0000-\u0000n\u0000o\u0000c\u0000h\u0000e\u0000k\u0000a\u0000i\u0000s\u0000e\u0000r\u0000:\u00001\u0000>\u0000,\u0000"
image = pipe(prompt).images[0]VBIN
- Prompt
- UNICODE refam, <lora:fam-lora-nochekaiser:1>,
Trigger words
You should use verybadimagenegative_v1.3 to trigger the image generation.
Download model
Weights for this model are available in PyTorch format.
Download them in the Files & versions tab.
- Downloads last month
- -
Model tree for Benevolent/VeryBadImageNegative
Base model
stabilityai/stable-diffusion-xl-base-1.0