Instructions to use tyfeld/MMaDA-Parallel-A with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use tyfeld/MMaDA-Parallel-A with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("tyfeld/MMaDA-Parallel-A", 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
Improve model card: Add pipeline tag, library, project page, abstract, visuals, and usage example
#1
by nielsr HF Staff - opened
This PR significantly enhances the model card for MMaDA-Parallel-A by:
- Adding
pipeline_tag: any-to-anyto accurately reflect its multimodal generation and editing capabilities, improving discoverability on the Hub. - Specifying
library_name: transformersbased on thetransformers_versionandauto_mapentries found in theconfig.jsonfile, indicating compatibility with the Hugging Face Transformers library. - Including a link to the official project website:
https://tyfeld.github.io/mmadaparellel.github.io/. - Adding the full paper abstract for a comprehensive overview of the model.
- Embedding relevant architectural and results images from the GitHub repository for better visualization.
- Integrating a practical "Quick Start" section with a bash command snippet directly from the GitHub README to demonstrate inference for MMaDA-Parallel-A. This ensures the usage example is accurate and directly sourced.
These additions will make the model more discoverable, easier to understand, and provide clearer guidance for users.