Generative Models

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

System Requirements

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

For Windows, 8GB VRAM is required for processing locally.

For MAC:

macOS 14 or higher is required for all generative models
Recover v1 is compatible with Intel Macs that have AMD Radeon graphics cards and at least 8 GB of VRAM
Recover v2 & Redefine are not compatible with Intel Macs and requires Apple Silicon with at least 12 GB of system RAM

For computers that are under the requirements, we recommend using cloud rendering.

Recover v2

Optimized for speed, Recover v2 is the updated version of Recover v1. This model brings the best fidelity in upscaling for extremely low quality images such as old photos or images with cityscapes.

It is recommended to use images that are 1000px and smaller to get the most optimized result.

How to Use Recover v2

Import your image
Under the Generative AI models, select Recover (by default, V2 is selected)
Use the Preview controls to adjust the size of the thumbnail.
Click anywhere in the Preview to begin the preview process.
Select Preview entire image button to see fully rendered image
Use the Detail slider to adjust and change the enhancement for a more refined output.
If satisfied with the results, click Export to keep your enhanced image. You can choose to export locally on your computer or via cloud rendering (highly recommended).

Redefine

Use this model to take your imagination to the next level. You can prioritize realistic upscaling for either fidelity or creativity.

It is recommended to use images that are 1024px and smaller to get the most optimized result.

Make the most of Redefine when you come across the following type of images:

Low resolution images (either from crop or otherwise)
Blurry images
AI-Generated images

For higher resolution images, try using our Basic models.

How to Use Redefine

1. Import your image.

2. Under the Generative AI models, select “Redefine”.

3. Move the mouse cursor to the Preview to select an area to click on to render a small preview.

4. To have more thorough control of the edits, select “Advanced settings”. You must turn on Advanced settings and set the Creativity level to 2-6 in order to access the prompt input box.

Face recovery toggled ON does not work for Creativity levels 3-6

Texture - refines details to more clarity
Extra sharpen - adds additional sharpening
Extra denoise - reduces noise further
Image description - Utilize the text prompt if you want to be extremely specific about the details you are looking for. The model responds more 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".

Check out the samples below to help inspire your next text prompt.

Text Prompt Samples

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

1. Candyland (an Ai generated image)

Prompt: "A city made of colorful cheeses"

2. A park in the city

Prompt: "a city at night with falling leaves"