SmartFreeEdit: Mask-Free Spatial-Aware Image Editing with Complex Instruction Understanding
Paper • 2504.12704 • Published
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("SUNQ111/SmartFreeEdit", 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]SmartFreeEdit: Mask-Free Spatial-Aware Image Editing with Complex Instruction Understanding
Qianqian Sun1*, Jixiang Luo2†, Dell Zhang2, Xuelong Li2
1 The University of Hongkong, 2 Institute of Artificial Intelligence (TeleAI)
Code
Please check our GitHub repository for code.
Demo
- Downloads last month
- -