ldiex

/

TACA

like 6

This PR significantly enhances the model card by incorporating more comprehensive information derived from the paper's abstract and the project's GitHub repository.

Key improvements include:

• Expanded "About" section: The brief description has been replaced with the full abstract of the paper, offering a detailed overview of the TACA method, its motivations, and findings.
• Visual Overview: An embedded GIF/video from the GitHub README is added for a quick visual summary of the model's capabilities.
• Detailed Usage Instructions: New Python code snippets using the diffusers library are provided for both Stable Diffusion 3.5 and FLUX.1, making it easier for users to integrate and experiment with TACA.
• Benchmark Results: The comprehensive evaluation table from the paper/GitHub repository is included, showcasing TACA's performance on the T2I-CompBench benchmark.
• Visual Showcases: Example generated images are added, with their paths corrected to ensure they render properly on the Hugging Face Hub.
• Citation Information: A BibTeX entry is added for proper academic attribution.

These updates aim to make the model card more informative, user-friendly, and aligned with best practices for documenting AI artifacts on the Hugging Face Hub.