Image-to-Image
Diffusers
StableDiffusionInstructPix2PixPipeline
image-editing
instruct-pix2pix
magicbrush
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("JovanHengGhimHong/magicbrush-diffusers", 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]MagicBrush Diffusers
Diffusers version of the MagicBrush model.
Citations
@inproceedings{zhang2023magicbrush,
title = {MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing},
author = {Zhang, Kai and Mo, Lingbo and Chen, Wenhu and Sun, Huan and Su, Yu},
booktitle = {Advances in Neural Information Processing Systems},
year = {2023}
}
- Downloads last month
- 18