Invisible Backdoor Triggers in Image Editing Model via Deep Watermarking
Paper • 2506.04879 • Published
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("yufengcccc/Backdoor_InstructPix2Pix_RoSteALS_CAT", dtype=torch.bfloat16, device_map="cuda")
prompt = "Turn this cat into a dog"
input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")
image = pipe(image=input_image, prompt=prompt).images[0]The model card of our paper Invisible Backdoor Triggers in Image Editing Model via Deep Watermarking
For more information, please refer to our Github
- Downloads last month
- 1