Skip to content

Image/Video Upscale & Interpolation

Choose a tag to compare

View all tags
@saddam213 saddam213 released this 14 Oct 20:53
· 33 commits to master since this release
v0.1.9
647d0eb
This commit was signed with the committer’s verified signature.
saddam213 Adam Clark
SSH Key Fingerprint: ewnBEXHp8fJq0n2RzK4DNknXtretrEoJPuCfp7CV5YE
Verified
Learn about vigilant mode.

TensorStack.Upscaler

The first official release of TensorStack.Upscaler, part of the TensorStack suite.
This library provides high-performance image and video upscaling using ONNX Runtime and supports both buffered inputs (e.g. file-based) and streaming sources (e.g. camera, pipeline, or frame feeds).

Key Features

  • Image Upscaling – Enhance image resolution with minimal loss in quality.
  • Video Upscaling – Process video frames from file or stream sources with synchronized output.
  • RIFE Frame Interpolation – Integrated RIFE model for smooth motion and higher effective frame rates.
  • Flexible Input Handling – Supports buffered and real-time processing pipelines.
  • TensorStack Integration – Built to work seamlessly alongside other TensorStack components like TensorStack.Image and TensorStack.Video.

Technical Notes

  • Built on ONNX Runtime with multi-provider support (CPU, CUDA, DirectML).
  • Compatible with TensorStack.Image & TensorStack.Video tensors.

Known Limitations

  • Interpolation and upscale models currently run sequentially per frame (parallel batching planned).
  • Limited metadata passthrough for streaming sources.

Docs & Examples

TensorStack.Upscaler Readme

Nuget Packages

https://www.nuget.org/packages/TensorStack.Upscaler
https://www.nuget.org/packages/TensorStack.Common
https://www.nuget.org/packages/TensorStack.Providers.CPU
https://www.nuget.org/packages/TensorStack.Providers.DML
https://www.nuget.org/packages/TensorStack.Providers.CUDA
https://www.nuget.org/packages/TensorStack.Image
https://www.nuget.org/packages/TensorStack.Image.Bitmap
https://www.nuget.org/packages/TensorStack.Image.BitmapImage
https://www.nuget.org/packages/TensorStack.Image.ImageSharp
https://www.nuget.org/packages/TensorStack.Video
https://www.nuget.org/packages/TensorStack.Video.Windows

Assets 14
Loading