Instructions to use o0o0o00o0/AlphaVAE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use o0o0o00o0/AlphaVAE with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("o0o0o00o0/AlphaVAE", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Enhance model card with metadata, paper link, code, and usage
#1
by nielsr HF Staff - opened
This PR significantly improves the model card for AlphaVAE by adding crucial metadata and comprehensive information.
Key changes include:
- Adding
library_name: diffusersandpipeline_tag: image-to-imageto the metadata for better discoverability and framework integration. - Including a direct link to the paper (AlphaVAE: Unified End-to-End RGBA Image Reconstruction and Generation with Alpha-Aware Representation Learning) for easy access to the research.
- Providing a link to the official GitHub repository (
https://github.com/o0o0o00o0/AlphaVAE) for detailed code, training scripts, and additional examples. - Adding a practical Python usage snippet that demonstrates how to load and use AlphaVAE with the
diffuserslibrary for RGBA image reconstruction. - Incorporating the main project image and the BibTeX citation for proper attribution.
These improvements make the model more informative, discoverable, and accessible for the community on the Hugging Face Hub.