SeedVR2 is an open-weight diffusion model package for restoring and enhancing images and videos in ComfyUI. It provides repackaged model files in multiple precision formats for local inference.
In the Image generation space, SeedVR2 takes a focused approach. It focuses on restoring and enhancing images and videos locally without relying on a hosted AI service. It is built as an open-source project for AI creators and ComfyUI users. SeedVR2 is open source under the GPL-3.0 license. It ships for the web, and it can be self-hosted.
Comfy Org builds and maintains SeedVR2, and it first shipped in 2026. Development happens publicly on GitHub with 73 stars and 14 commits in the last 90 days. Key capabilities include video restoration, image restoration, and diffusion model.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do