Generative Models

Introduced in v7.1.0, Gigapixel now has generative AI models that produce outstanding results for more powerful enhancements.

System Requirements

Recover and Redefine have higher requirements for processing than the core models.

Recover v2

Optimized for speed, Recover v2 is faster than Recover v1. This model brings the best upscaling fidelity for old and low quality photos.

Using Recover v2

1. Import your image
2. Under the Generative header, select Recover
3. Use the preview controls to adjust the size of the thumbnail
   Click anywhere in the viewer to begin the preview process
   Or, select Preview entire image button to see a whole image
4. Use the Detail slider to adjust enhancement as desired
5. Click Export to keep your enhanced image
   Choose to export locally on your computer or upload for Cloud rendering

Pre-downscaling

Introduced in v8.4.0, an action for pre-downscaling has been added to 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 sharpness and detail
• Choose between four levels of downscale intensity
• Users can test the intensity with the Preview controls

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 BETA

For use with low quality or AI generated images, use Redefine to add definition and detail. You can prioritize upscaling for either realistic fidelity or creative distinction.

Using Redefine realistic

1. Import your image
2. Under the Generative header, select “Redefine realistic”
3. Choose between None or Subtle to set the level of adjustment that will be applied
4. Selecting Subtle will enable the option for directing the adjustment using the Image description
5. Use the preview controls to adjust the size of the thumbnail
   Click anywhere in the viewer to begin the preview process
   Or, select Preview entire image button to see a whole image
6. Click Export to keep your enhanced image
   Choose to export locally on your computer or upload for Cloud rendering

Using Redefine creative

1. Import your image
2. Under the Generative header, select “Redefine creative”
3. Choose between Low, Medium, High, or Max to set the level of adjustment that will be applied
4. Use the Image description to direct the changes that will be applied to the image
5. Adjust the Texture slider to refine the results
6. Use the preview controls to adjust the size of the thumbnail
   Click anywhere in the viewer to begin the preview process
   Or, select Preview entire image button to see a whole image
7. Click Export to keep your enhanced image
   Choose to export locally on your computer or upload for Cloud rendering

• Creativity - Low, Medium, High, Max
• Image description - Utilize this if you want to be specific about the details you're looking for. The model responds to a descriptive statement versus a directive one. For example, use the phrase "girl with red hair and blue eyes" instead of "change the girl's hair to red and make her eyes blue"
• Texture - adjust the level of detail that will be generated

Image Description

Samples show both before and after where the creativity has been pushed up significantly.

Candyland (AI generated)

"A city made of colorful cheeses"

A park in the city (photograph)

"A city at night with falling leaves"

Check out the Community pages for tips on writing image descriptions from other users.