Instructions to use Windsrain/ZeroStereo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Windsrain/ZeroStereo 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("Windsrain/ZeroStereo", 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
Improve model card for ZeroStereo (StereoGen): Add tags, paper info, links, and usage
#1
by nielsr HF Staff - opened
This PR significantly enhances the model card for the Windsrain/ZeroStereo model by:
- Adding
pipeline_tag: image-to-imageandlibrary_name: diffusersto improve discoverability and specify compatibility. - Including the paper title, abstract, and a link to the Hugging Face paper page.
- Providing a direct link to the official GitHub repository for comprehensive code and usage details.
- Adding a basic Python usage example for loading the model with
diffusers. - Incorporating key information from the original GitHub README, such as pre-trained models and acknowledgements.
- Adding a BibTeX citation.
- Removing the irrelevant "File information" section.
Windsrain changed pull request status to merged