InstantDrag: Improving Interactivity in Drag-based Image Editing
Paper • 2409.08857 • Published • 34
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("alex4727/InstantDrag", 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]InstantDrag
This repository contains the checkpoints of the paper InstantDrag: Improving Interactivity in Drag-based Image Editing.
- Downloads last month
- 76