Instructions to use To-Hitori/GeoMVD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use To-Hitori/GeoMVD 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("To-Hitori/GeoMVD", 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
Update pipeline tag, add library name, and expand model card for GeoMVD
#1
by nielsr HF Staff - opened
This PR significantly improves the model card for GeoMVD by:
- Updating the
pipeline_tagfromimage-to-imagetoimage-to-3dto accurately reflect the model's capability in multi-view generation for 3D reconstruction. - Adding
library_name: diffusersto enable the "how to use" widget, as the model's architecture (identified inmodel_index.json) is compatible with thediffuserslibrary. - Expanding the model description with an introductory summary and the full paper abstract.
- Adding direct links via badges to the Hugging Face paper page, the project page, and the GitHub repository.
- Including the installation instructions and a detailed "How to Use" section with code snippets directly from the GitHub README to guide users on inference.
- Incorporating the citation and acknowledgements sections for proper attribution.