wyh6666

/

InsViE

like 0

This PR significantly enhances the model card for InsViE-1M by:

• Adding the pipeline_tag: text-to-video, enabling the model to be found at https://huggingface.co/models?pipeline_tag=text-to-video.
• Adding library_name: diffusers for better integration and discoverability.
• Including relevant tags such as video-editing, instruction-tuned, and video-generation for improved categorization.
• Linking to the official Hugging Face paper page: InsViE-1M: Effective Instruction-based Video Editing with Elaborate Dataset Construction.
• Including comprehensive links to the GitHub repository, Hugging Face Dataset, YouTube demo, and a Hugging Face Space demo.
• Providing a detailed overview, key features, and comprehensive usage instructions directly from the original GitHub repository.
• Adding a visual demo to showcase the model's capabilities.

Please review and merge this PR if it accurately reflects the model's information.