Use Upscale to increase the number of pixels in your image.

There are two methods to resize your image:

 - upscale your image by a multiplier of up to 6x

- upscale your image by inputting a custom width or height

In the "Scale factor" field, type in your multiplier

The dimensions of your image automatically adjust after you set the scale. Custom scales can be specified by up to 2 decimal points.

The default PPI is 300. You can change this in your Preferences panel. 

 scale to enhance your image without upscaling

Go to your Settings in the Topaz Gigapixel AI menu, click Settings...
On Windows, Preferences is located under 

Introduced in v8.2.0, image batches can be scaled by the longest side. 

To enable longest side, select which images you want to upscale by clicking the check boxes in the file list. 

When multiple images are selected, the Dimensions show 

 indicating that there are multiple values across all images. 

The longest side option does not appear when only one image is selected. 

Upscale 

AI Models are the program filters Topaz Labs has created to determine how to adjust or enhance your images, graphics, digital scans, or artwork.

Core AI Models

Generative Models

Legacy Models

Explore each section to find the one that's best for your images. 

AI Models

Use "Settings" to customize your enhancements 

 - 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.

Settings

Utilize Face Recovery to improve images where facial attributes could be enhanced. Low resolution, blurry, and unclear details of human faces are best used for this feature.

 detects and recovers human faces. It works best on blurry, low-resolution, or poor-quality faces, but may remove detail from high-quality faces.

 - detects high and low confidence faces to enhance.

When enabled, the AI scans the entire image, searching for the eyes, nose, and mouth of a human face.

It determines the number of faces recognized and categorizes them into two types: 

: AI analysis distinguishes clear details of the eyes, nose, and mouth, recognizing a face.

 faces that lack detail, are out of focus, or partial faces where the head is turned away.

The Face Recovery model does not use Generative Al or diffusion models. It is trained from digital images from digital cameras. Certain types of images, such as old scanned photographs, are not always easily recognized.

 Creativity values 3-6 in order to maintain the best creative results from the model.

Then click on the Face recovery switch to activate the feature.

 to make a selection of the desired faces.

In the Preview, the image shows boxes around faces that the AI has detected. Click on the desired boxes that need enhancement.

A dark gray box indicates a High Confidence result.
A light gray box indicates a Low Confidence result.

Click on any boxes you wish to enhance, and the selected faces will appear blue.

After the AI model finishes enhancing, use 

 by adjusting the slider to change the effect on the face. Increasing or decreasing the value will adjust the intensity of the enhancement. Skin can appear smoother or clearer depending on the strength.

Animal faces are not detected in Face Recovery.

Officially released in v8.3.0, this AI model now adds another layer of enhancement possibilities that Gen 1 did not offer. 

Our models are designed to preserve the original image, but since Face Recovery is specifically designed to reconstruct damaged faces, the model will sometimes change expressions slightly or may smooth skin, hair, or small facial details.

This version not only improves upon Gen 1, but also offers two modes: 

 mode closely mirrors the original Face Recovery model, but with improved overall quality. For scenarios with very low resolution or tiny faces, 

 mode generates additional details that might be missing from the original image, producing high-quality results even from very low-resolution inputs. It’s incredible what can be achieved with just a few pixels. Note that the Creative mode does not use a diffusion-based generative model, so if you prefer traditional machine-learning models, Gen 1 Face Recovery is still a great option.

Check out these two modes in action here.

The example below showcases the difference between Gen 1 & Gen 2, Realistic & Creative. Notice that certain facial features are altered differently in Creative mode. 

Set Face Recovery strength to 80 when using the models, as this blends well with the original image to preserve more faithful detail.

Images that are most optimized with this model are:

Face Recovery

 processes the image in a higher gamma color space. For images with highly saturated colors, this can enhance AI outputs with more details and less color bleed.

Gamma Correction is also best used for very dark, low light images with lots of noise. 

Use the toggle switch in the right panel to enable. 

Gamma Correction

Functions

Cloud Rendering

Summary of all available Filters within Topaz Gigapixel AI. These features are enhancements created to support the use of upscaling for the best output possible.

Filters Panel

Upscale

AI Models

Settings

Face Recovery

Gamma Correction