Understand the Topaz Photo AI user interface.

The interface is divided into 8 sections.

The preview will show the changes made to the original image when the preview is done processing.

 You can zoom in/out with the scroll wheel and drag the view to inspect parts of the image.

Click and hold the preview or hit the spacebar to view the original image.

Use the scroll wheel to zoom or change the zoom with the dropdown menu.

Select how to display the preview from the menu on the bottom right. There are 3 configurations. 

The entire preview is populated by the edited version.

The image is split by a white line, with the original version displayed on the left and the edited version on the right. Click and drag the line across the image to view the edit.

You can view the original version and the edited version side-by-side to compare them.

The mini preview displays the entire image and is an easy way to pan around the image to sections you want to view.

This section displays three important sections: Autopilot, image quality, and upscale settings. Adjust the filters in this panel to edit the image. 

This indicates the state of the preview, if it's currently processing or completed. Change a filter setting or moving the view will force the preview to reprocess.

This will indicate which file is selected and the software you are using. It'll also display the software version number.

This button will indicate if there is an update available. Click it to view the release notes and update Topaz Photo AI.

Windows

The Preferences menu allows you to toggle on/off various settings and configure the app to your needs. 

The Autopilot tab controls the AI filters and strength automatically applied to images. 

Learn about the Autopilot and controls here in the Autopilot article.

AI Processor: Select which processor you want to use to run the software

Lens Correction: This corrects optical distortions introduced by camera lenses to produce a more accurate image.

Close Images After Saving: Automatically close the image file after you save it to streamline your workflow.

Show Help Prompts: Receive helpful tips when relevant with suggestions on how to improve your experience.

You can open and close images and locate them in your computer.

By default, none of the image editing options in “Edit” are available until an action has been performed on the image.

In the “Edit” option, you can manage the Mask and Autopilot settings, which become visible once you make adjustments in the image settings panel on the side.

You can zoom in and out, as well as zoom to fit your page.

In addition to the “View” option, there are 2 other ways to zoom in and out of the image.

Choose your preferred zoom percentage from the dropdown menu located at the bottom right corner.

Scrolling on your mouse will also allow you to zoom in the same increments as the dropdown menu.

The “Help” option is where you can access tools to assist with using the software.

Give Feedback: This directs you to the general section of the community forum page. 

Report An Issue: This directs you to a section of the community forum to report details for bugs.

Technical Support: This directs you to articles with instructions and advice for particular issues. 

Product Roadmap: This directs you to descriptions of product updates. 

Release Notes: This directs you to the technical documentation produced and distributed alongside the launch of a new update.

Open Log Folder: This opens the  file that contains data about usage patterns, activities, and operations within the software.

User Interface

Autopilot is your image quality specialist built into Topaz Photo AI. It analyzes your image for:

Metadata - such as ISO, camera information, and lens information

The Autopilot status and analysis appears in this panel on the top right of the window when a new image is loaded in.

After the analysis, Autopilot selects the AI filters and settings needed to optimize the image based on the Preferences > Autopilot menu. Green lights appear next to Autopilot selected AI filters and settings.

Personalize Autopilot from the Preferences menu.

Click the Save button after your changes to apply the current settings to all images in the current session and future sessions.

Subject Detection controls the model used for subject masking and sharpening. Click on the dropdown menu to view the options.

: identifies and selects an object in focus

: identifies land or water in focus and deselects sky

This controls Autopilot Upscale & Resize settings for:

minor denoise and minor deblur strength based on detected noise and blur

Set the height, width, long edge, short edge, or scale factor (2x, 4x, 6x) for all images on Autopilot. Images are upscaled to reach the selected dimension. Images larger than the selected output size are not upscaled.

Scale can be used to downscale images to 0.2x the starting size. No other option downscales images automatically.

When using height, width, long edge, or short edge, the dimensions can be changed from pixels to inches or centimeters. This will let you control the print resolution when paired with Output Resolution.

Set to Preserve Original Resolution by default. Set Default Resolution to select a resolution for all processed files.

The default setting, automatically upscales small images to 12 megapixels or a maximum of 6x the original size.

Images larger than 12 megapixels are not upscaled.

Pick a specific AI model for upscaling all your images. 

Modifies the Autopilot recommended noise removal strength lower or higher when resizing any image.

Modifies the Autopilot recommended sharpen strength lower or higher when resizing any image.

This controls Autopilot Remove Noise settings for:

default Remove Noise strength based on detected blur

Non-Raw and Raw files are treated differently because they use different Remove Noise models. Remove Noise - Raw has a separate section under the non-Raw controls.

When detected noise is at or above a set amount, Remove Noise is automatically turned on.

When detected noise is below the selected level, Remove Noise is not turned on.

Set to Autopilot Off if you do not want Autopilot to turn on Remove Noise automatically.

Pick a specific AI model for denoising all your images. 

Modifies the Autopilot recommended denoise strength lower or higher when the AI filter is turned on.

This controls Autopilot Sharpen settings for:

default Sharpen strength based on detected blur

When detected blur is at or above a set amount, Sharpen is automatically turned on.

When detected blur is below the selected level, Sharpen is not turned on.

Set to Autopilot Off if you do not want Autopilot to turn on Sharpen automatically.

Pick a specific AI model for sharpening all your images. 

Modifies the Autopilot recommended sharpen strength lower or higher when the AI filter is turned on.

Face Detection controls which faces are automatically selected to recover and the default Face Recovery strength. Click the dropdown menu for face selection settings:

: low quality faces are selected improved

: faces in the subject mask are selected and improved

: face detection is turned off and no faces are improved

All faces processed will use the selected Face Recovery Strength.

Parts to Enhance controls areas near the face which are improved.

Deselect Hair and Neck to improve only the face.

Selecting None disables face detection and will reduce processing time if your images have no faces to recover.

This controls the default strength for the exposure and contrast correction when it is turned on.

This controls the default temperature and strength of the color correction on the image.

Return Autopilot to normal behavior by clicking "Reset to default settings" at the bottom of the menu. This will set controls to:

Autopilot & Configuration

The Remove Noise filter will detect and remove noise caused by: 

inconsistency in the sensor used for image capture

Topaz Photo AI comes with five Remove Noise models, each trained for a different situation. 

The Raw models are enabled when Topaz Photo AI detects a Raw file. They process Raw Bayer sensor data, which contains the more information and detail than pixels, to remove noise. 

Raw images which do not have Bayer sensor data will not use the Raw models.

For non-Raw images such as TIF, JPG, PNG, etc, the normal Remove Noise models are used. The non-Raw models process pixel data to remove noise.

Use Raw images with Topaz Photo AI to enable the Raw Remove Noise models and get the best noise reduction for your image.

The same image processed as Raw vs TIF is below. Original image (left), Raw result, TIF result (right).

Enabled when an image with Raw data is detected. Processes the sensor color filter array data to detect and remove noise. Best for low-medium noise images.

Enabled when an image with Raw data is detected. Processes the sensor color filter array data to detect and remove noise. Best for medium-high noise images.

A beta model that will eventually replace Raw Normal. It retains more detail for a high quality denoise that does not smooth out the image.

A beta model that will eventually replace Raw Strong. This model will retain more detail than the Raw Strong model while removing extreme noise at very high ISOs.

Enabled for non-Raw images. Processes pixel data to detect and remove noise. Best for low-medium noise images.

Enabled for non-Raw images. Processes pixel data to detect and remove noise. Best for medium-high noise images with better detail retention and controls.

Enabled for non-Raw images. Processes pixel data to detect and remove noise. Best for medium-high noise images.

Enable/disable Remove Noise by clicking the toggle.

When turned on, Remove Noise displays a Strength, Detail, Recover Original Detail slider. Control the results with these options.

: controls the amount of noise removed from the image. Increasing the Strength slider can remove fine details.

: controls a minor sharpening on the entire image. Use this slider to recover details that are lost during noise reduction.

: Return texture and fine details lost during noise reduction. Start at low values and slowly increase.

The Raw models require Bayer sensor data. If the Raw image does not have Bayer sensor data, the Raw models cannot be used.

Fujifilm cameras with X-Trans sensors are not compatible with the Raw models as they do not create Bayer sensor data. The Remove Noise - Linear Raw model will be used instead.

Raw files which are processed and are no longer in the Raw Bayer sensor format are not compatible with the Raw models. The Remove Noise - Linear Raw model will be used instead.

There are two alternatives if Remove Noise removes too much detail and  low noise reduction is needed:

Enable the Sharpen filter and increase the Clean slider

Enable Enhance Resolution and increase the Suppress Noise slider

The Sharpen - Minor Denoise slider performs a mild noise reduction on the subject in the image.

The Enhance Resolution - Minor Denoise slider performs a minor noise reduction to the entire image.

Remove Noise - Raw & non-Raw

The Sharpen filter detects existing details in the image and uses them to recreate details lost to blur. 

Use it to save your blurry images caused by:

Topaz Photo AI comes with five sharpen models, each trained for a different situation.

Use the Standard model to avoid over-sharpening which can make your image look unrealistic.

Best for low-to-medium soft and blurry images. This model is for all-purpose sharpening.

A new beta model which will replace Standard for low-to-medium blur images.

Best for medium blur and out-of-focus images. This model performs a medium strength sharpening to bring the image into focus. 

Good for medium-blur and out-of-focus images. This model performs a strong sharpening for blurry images.

Good for medium-blur and streaking in images. This model performs a strong sharpening to correct movement.

Enable/disable Sharpen by clicking the toggle.

When turned on, Sharpen displays four AI models, a Strength slider, a Clean slider, the Subject Only toggle, and the Edit Subject button. Control the sharpen effect with these options.

: increases detail. Too much sharpening can create an unrealistic result.

: removes noisy pixels that hide details. This is for the Standard, Lens Blur, and Motion Blur models.

: this toggle controls where sharpening is applied. Toggled on, only the subject is sharpened. Toggled off, the entire image is sharpened.

: opens the masking controls to change the subject mask.

Sharpen is usually best when used selectively on the main subject of the image.

There are two alternatives if Sharpen over-sharpens the image or a low sharpening is needed:

Enable the Remove Noise filter and increase the Minor Deblur slider

Enable Enhance Resolution and increase the Minor Deblur slider

The Remove Noise - Minor Deblur slider increases sharpness for the entire image.

The Enhance Resolution - Minor Deblur slider performs a slight sharpening on the entire image.

Sharpen

Autopilot will automatically analyze your image to mask the subject. This mask is used primarily to selectively 

Hover over the "Subject" text in to view the current mask.

Click the Subject button under the preview or the Edit Subject button in the Sharpen filter to open the masking menu.

The masking menu includes AI models for automatic subject detection, mask feathering, and two brushes for manually changing the mask.

The subject detection comes with three models and a None option to turn off automatic detection.

The feathering slider increases the mask softness at the edges. Less sharpening is applied at the edges. Comparison below is feathering at 0 (left) and 100 (right).

The overlay color and opacity will change the mask visibility. This does not affect the sharpening.

Topaz Photo AI comes with two brushes of varying sizes. Swap between them with this toggle.

This brush creates and selects groups of pixels. Patch size can be increased with the menu below.

A circular brush. Brush size can be increased with the menu below.

Brush the image by selecting Add or Subtract. Click and drag on the image to brush. Right click to use the unselected option.

if Add is selected, right click Subtracts

if Subtract is selected, right click Adds

Clear Strokes removes all user changes to the mask.

Configure Autopilot For Subject Selection

Change the default subject type in the Autopilot settings. Navigate to the Preferences > Autopilot menu. Default Subject Type will let you pick the subject detection model used for every image. 

Subject Mask & Refine

Upscaling/Resizing intelligently generates new pixels to increase image size and improve image quality. AI models improves image quality to clean up imperfections due to minor noise and reduces blurry edges to increase detail. 

Images can be scaled from a minimum 0.2x to maximum 6x or 32,000 pixels on the longest edge. Scale by 1x to improve image quality without resizing the image.

Turning on Resizing will automatically upscale to 2x when enabled.

The Resize menu displays the following information:

scale options, with shortcuts for upscaling 2x, 4x, 6x (Max)

units for dimensions and a resolution section when Inches (In) or Centimeters (Cm) is selected

You can manually input the output scale and or width/height dimensions. Click on the PX unit for a dropdown with In or Cm. Select In or Cm to display resolution and enter the output file resolution.

For printing, the most common resolution used is 300 pixels per inch (PPI).

Scale an image by 1x to maintain image size and increase image quality by to clean up imperfections due to minor noise and reduces blurry edges to increase detail. 

Images can be downscaled (smaller than the original size) to decrease the image size while maintaining the highest quality possible.

Topaz Photo AI will upscale your image width and height up to 6x in one pass. The maximum image size it can output is 32,000 x 32,000 pixels (1024 megapixels) pixels.

To upscale an image more than 6x, you can process the image in Topaz Photo AI a second time.

Upscale/Resize comes with four AI models.

For medium-quality images from point-and-shoot cameras and older smartphones

For high-quality images from DSLRs and most modern smartphones

For low-quality images that have been highly compressed

Enable/disable Upscale/Resize by clicking the toggle.

The AI models have up to three sliders to control the processing:

: improves the details by correcting pixels on edges

: reduces distortion due to low starting quality

Upscale & Resize

Click the Crop button on the top right under the preview to enter the crop menu and change the input image size.

By default, the aspect ratio is locked to the dimensions of the original image. Click the dropdown to select commonly used aspect ratios. 

Click the Lock or Custom to unlock the aspect ratio and manually change the crop rectangle size.

Move the crop handles to change the crop area.

Click Reset to return the original image size. Click the Apply button to save the selection.

Crop

This filter detects faces in your image and increases face quality.

Autopilot face detection and strength are controlled from the following menu:

The Face Detection menu will let you control:

which faces are selected to recover automatically

Set the default strength to your preference.

Parts to Enhance lets you deselect areas around the face to control processing. Deselect:

Hover over the "Faces" text in the autopilot to view the faces detected.

faces selected for processing are outlined in yellow.

low confidence faces are outlined in dim grey.

By default, only high confidence, low quality are selected for recovery. Low confidence faces must be added manually for recovery.

To select/deselect faces for processing, click the Select button in Autopilot section or in the Recover Faces filter and open the Select Faces menu.

Decide which faces to recover in this menu. In general, pick important faces to improve and leave the rest to become part of the background.

Click on a face to select it. The buttons in the right menu let you quickly select or deselect faces.

Select All faces enables every face for recovery, including low confidence faces

Quick Select lets you easily select groups of detected faces.

Apply your changes by clicking the Apply button at the bottom.

This filter improves faces in the image by detecting details in the face and constructing a high quality version that is blended with the current face. For best results, control the strength to blend the generated face with the original face and the rest of the image. This creates a realistic, high quality result.

For low confidence and low quality faces, this filter can generate an unfamiliar face as there is limited detail about the original face.

Recover Faces & Select Faces

The Preserve Text filter improves text to make it clear and easily readable.

Using multiple AI filters can layer artifacts that ruin text. Preserve Text should always be used in these cases to reverse the effect.

Features

User Interface

Autopilot & Configuration

Remove Noise & Raw Remove Noise

Sharpen & Refine Mask

Recover Faces & Select Faces

Preserve Text

Enhance Resolution

Upscale & Crop

Remove Object

Saving