Seedvr 3B
ByteDance's Seedvr 3B is a diffusion transformer model designed for generic video restoration, exceling at arbitrary-resolution restoration without relying on pretrained diffusion priors. It is notable for its large scale, serving as the largest-ever diffusion transformer model for this task.
Input
Output
Context
-
Max Output
-
Parameters
3B
Technical Specifications
Model TypeVideo
Context WindowNot available
Max Output TokensNot available
Parameters3B
Release DateJun 11, 2025
Training CutoffNot available
Licenseapache-2.0
Open SourceYes
Input Modalities
Video
Output Modalities
Video
Capabilities
Estimated GPU Requirements for Seedvr 3B
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.