Take almost any video to 4K

Project Starlight uses diffusion technology for the clearest AI video enhancement to date. It upscales, enhances, denoises, de-aliases, and sharpens video—without any sliders or manual adjustments.

For even the most challenging footage.

—The first-ever diffusion tool for video restoration

While popular tools like Runway and OpenAI's Sora use diffusion AI technology to generate new footage, Project Starlight has optimized it for improving existing footage. This “first” makes it a huge leap forward for video restoration and enhancement.

Smooth, natural motion.

—The first enhancement tool to solve temporal consistency

Each frame restored by Project Starlight is created by analyzing hundreds of frames surrounding it. This creates a smooth quality that has never been achieved in AI footage restoration before, called temporal consistency. It’s one of the most important breakthroughs in Project Starlight and signals a new future for video restoration.

Details, more detailed.

—The highest visual quality difference ever achievable in video

While existing video enhancement models utilize GAN technology, the switch to diffusion is one key to Project Starlight's major quality boost.

Unlike existing GAN models, Project Starlight’s models have a great understanding of semantics, what objects actually are, and how motion and physics work—so they can make things look more natural with less to work with.

Currently, diffusion models are larger and slower than existing methods, so Project Starlight is only available in cloud rendering. It will continue to evolve in development—pushing for speed and size in the coming months.

Users can access the Project Starlight research preview online, or in Video AI.

Anyone interested in extended use of the research preview can reach out via email to enterprise@topazlabs.com.