Skip to main content
The HitPaw Video Enhance node uses an external API to improve the quality of videos. It upscales low-resolution videos to a higher resolution, removes visual artifacts, and reduces noise. The processing cost is calculated per second of the input video.

​
Inputs

​
Common Inputs

​
Portrait Restore, General Restore, and Ultra HD Model Inputs

These resolution options are shared by Portrait Restore Model (1x), Portrait Restore Model (2x), General Restore Model (1x), General Restore Model (2x), General Restore Model (4x), and Ultra HD Model (2x).

​
Generative Model (1x) Inputs

Notes:
  • The input video must be between 0.5 seconds and 60 minutes (3600 seconds) in duration.
  • The selected resolution must be at least as large as the input video’s dimensions. For square videos, it must be at least as large as the video’s width and height. For non-square videos, it must be at least as large as the video’s shorter dimension. If the target resolution is smaller, an error is raised. Selecting "original" keeps the input video’s resolution.
  • When a resolution other than "original" is selected, non-square videos are scaled so that their shorter dimension matches the selected resolution while preserving the aspect ratio. Square videos are scaled so that both dimensions match the square target size of the selected resolution (for example, "4K/UHD" produces 2048×2048).

​
Outputs

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
Source fingerprint (SHA-256): 42803c7137d62dbce5021cd2bd9b9fba1a89c80e7b3f237f8a0eb03858c49967