Instruct-CLIP: Improving Instruction-Guided Image Editing with Automated Data Refinement Using Contrastive Learning
Paper • 2503.18406 • Published • 3
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("SherryXTChen/LatentDiffusionDINOv2", 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]This model has been pushed to the Hub using the PytorchModelHubMixin integration: The model is based on the paper Instruct-CLIP: Improving Instruction-Guided Image Editing with Automated Data Refinement Using Contrastive Learning. GitHub: https://github.com/SherryXTChen/Instruct-CLIP.git
- Library:
torch==2.4.0 torchvision==0.19.0 diffusers==0.30.3 transformers==4.45.2 - Docs: See our repo for more information.
- Downloads last month
- 6