This repository is a curated list of recent diffusion models and research papers focused on video generation, editing, restoration, and understanding. It serves as a comprehensive resource for researchers, engineers, and practitioners in the field of AI-powered video synthesis.

How It Works

The project acts as a living bibliography, categorizing and linking to a vast array of open-source toolboxes, foundation models, evaluation benchmarks, and specific research papers. It covers diverse applications such as text-to-video, image-to-video, video editing, controllable motion, long video generation, and 3D/physical priors.

Quick Start & Requirements

This is a curated list, not a runnable codebase. To use any of the listed models or toolkits, refer to their individual project repositories.

Highlighted Details

• Extensive coverage of over 500 research papers and projects, categorized by application area.
• Includes commercial products like Sora, Veo, and Kling alongside open-source efforts.
• Features a dedicated section for evaluation benchmarks and metrics for video generation models.
• Covers emerging areas like 3D/physical priors, AI safety, and applications in healthcare.

Maintenance & Community

The list is actively maintained by showlab, with contributions likely from the broader AI research community. Specific community links or active development status for the curated list itself are not detailed.

Licensing & Compatibility

The licensing of the curated list itself is not specified. However, the individual projects linked within the list will have their own respective licenses, which may vary from permissive to restrictive.

Limitations & Caveats

As a curated list, this repository does not provide any executable code or direct functionality. Users must navigate to individual project links to access and utilize the described models and tools. The sheer volume of information may require significant effort to sift through for specific needs.