Settings

Use model settings to customize your enhancements. As a dedicated upscaler, Topaz Gigapixel features upscale models intended for increasing pixel dimensions while maintaining the original image as much as possible.

Denoising and Sharpening only apply with regards to the upscaling process. For dedicated Denoise and Sharpen tools, look to Topaz Photo.

We recommend applying Auto Mode as a starting point.

Core Model Settings

Common settings for core models:

  • Denoise slightly suppresses noise
  • Sharpen attempts to reduce motion or lens blur
  • Fix Compression reduces compression artifacts to improve details

These options have a sliding degree of intensity. You can input a custom value from a scale of 1 to 100. When Auto Mode is enabled, dots will appear next to the setting name.

Denoise and Sharpen values can also be seen in the file list.

Generative Model Settings

Unique settings for Wonder, Standard Max, Recover, and Redefine can be found under Generative Models.

Recover 2 Pre-downscaling

An action for pre-downscaling will improve working with larger images that suffer from false resolution. These images tend to be low information dense—where pixel dimensions have increased without a meaningful addition of detail. Pre-downscaling addresses this by intelligently optimizing image input before enhancement.

How it works:

  • Pre-downscaling resamples the image to concentrate image density
  • The result is then upscaled using AI to generate natural results
  • Choose between three levels of downscale intensity

When to use Pre-downscaling:

  • When images exceed 1000px on both sides
  • Ideal for old JPEGs, scanned photos, or poorly upscaled content
  • Select None if you prefer to skip pre-downscaling

Redefine Creative Settings

  • Creativity will provide various levels of change
  • Image description helps guide the AI for desired results
  • Texture gives degrees of definition to the image

Auto Mode for Redefine creative will clear the Image description and set the Texture slider value.