MagicQuill: An Intelligent Interactive Image Editing System
Paper • 2411.09703 • Published • 80
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("LiuZichen/MagicQuill-models", 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]Model Checkpoints for project.
The paper is MagicQuill: An Intelligent Interactive Image Editing System.
- Downloads last month
- -