AURORA
Collection
Repository: https://github.com/McGill-NLP/AURORA • 5 items • Updated • 5
Image-to-Image
Diffusers
Safetensors
English
StableDiffusionInstructPix2PixPipeline
editing
vision-language
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("McGill-NLP/AURORA", 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]For more details: https://github.com/McGill-NLP/AURORA or read the paper: https://arxiv.org/abs/2407.03471
Citation
@inproceedings{krojer2024aurora,
author={Benno Krojer and Dheeraj Vattikonda and Luis Lara and Varun Jampani and Eva Portelance and Christopher Pal and Siva Reddy},
title={{Learning Action and Reasoning-Centric Image Editing from Videos and Simulations}},
booktitle={NeurIPS},
year={2024},
note={Spotlight Paper},
url={https://arxiv.org/abs/2407.03471}
}
- Downloads last month
- 13