Instructions to use RyanHangZhou/PICS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use RyanHangZhou/PICS with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("RyanHangZhou/PICS", 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] - Notebooks
- Google Colab
- Kaggle
metadata
license: mit
datasets:
- Heatmob-Research/VITON-HD
- Voxel51/LVIS
- jxu124/objects365
- Oursel/cityscapes
- paidaixing/Image_mapillary_Street_level
- dgural/bdd100k
language:
- en
pipeline_tag: image-to-image
library_name: diffusers
tags:
- art
PICS: Pairwise Image Compositing with Spatial Interactions
|