AI Models
AI Models are the program filters Topaz Labs has created to determine how to adjust or enhance your images, graphics, digital scans, or artwork.
Standard
The Standard AI Model is the overall recommended model to use across a variety of images. This model has been trained to see a variety of files but works best for photos, graphics, and generated images.
Standard v2, first introduced in version 7.0.0, is the default version in 7.1.0
Standard v2 reduces blurry patches that occurred in Standard v1.
High fidelity
The High Fidelity AI Model is trained to study high quality images with high resolution. Images from high end cameras are best. This filter can maintain the original look of images, without creating distortions.
This model intends to keep the original look of the image. It can be the most common upscaling filter after other denoise/sharpen filters.
Preserve the textures and authentic capture capture details with High Fidelity and minimally change details using the Denoise slider.
Standard v2 addresses more natural textures preserving them while maintaining sharpness.
This particular model has a slower processing time in order to produce better output results.
To keep the look of grain or noise in the image, tune down the Denoise and Fix Compression sliders for more natural results.
Low resolution
Low resolution files are commonly identified as having fewer pixels. This model works best with screenshots, images pulled from the web or images with 72 pixels per inch (ppi).
Low resolution v1 (Legacy Model as of v.7.1.0) v1 is trained to remove more blur by default.
Text & shapes
Text & shapes enables more distinct patterns and shapes during upscaling with man-made objects, textures, and even written text and fonts.
This AI model is suitable for graphic design, typography, images with street signs, or text on architecture, automobiles, etc.
Photo courtesy of Fondo Antiguo de la Biblioteca de la Universidad de Sevilla
Art & CG
The Art/CG AI Model is best for artwork, drawings, illustrations, and computer generated graphics like Midjourney
Midjourney Illustration created by legendary_fox_47504
Very Compressed
The Very Compressed AI Model is best used for images with a lot of compression artifacts. Use this for images saved at a small size, scanned images or old digital images.
Lines
The Lines AI Model emphasizes and heavily contrasts lines for architecture, cityscapes, and any image with thick lines.
Recovery
Recovery AI Model recognizes pixels and gives creative results. Designed with graphic designers, photographers, and web developers in mind, this model helps improve low resolution image quality from extremely small sized dimensions.
This Ai Model is currently in Beta version. There are a list of common conflicts and known issues that comes with attempting to use Recovery. Please review the Recovery FAQs before proceeding to run this AI model.
How to run Recovery
1. Import your image and select an upscale size, then click on Recovery.
In “Settings”, there are two Recovery modes:
- Quality - for generative details for images that are less than 1000px on its longest side. The wait time is significantly longer but the quality results are the highest. (Quality is recommended for computers that have at least 16GB of VRAM)
- Speed - for quicker previews and rendering resulting with the trade off of the output results being less optimized than the Quality mode
2. Once you’ve made your Recover mode selection, choose a Preview size.
This preview size turns your cursor into a square of varying sizes. This square is the actual preview shown.
3. Hover around your main image and select an area that you would like to see a preview of your Recovery mode.
You can select up to 3 different previews when using Recovery each time. Preview sizes can be changed at any time and preview boxes can overlap on top of each other.
A fourth time of using the preview will remove the first preview box selected.
When using Quality mode, the Detail slider bar is available to increase the degree of the results. Turn on Auto mode for suggested detail. You can change these Details after you click Run recovery. Speed mode does not have a Detail slider.
To reset all previews, click on Clear preview.
4. To approve and begin full recovery on your image, click on Run recovery. You must Run recovery to keep the results of your image if you are working on other images.
A Pop up box shows the Rendering image time.
To stop the processing, click Cancel or allow Rendering to finish.
5. Once rendering is complete, you can click Export image to save your image.
Check out the Sample image used in Recovery with both modes.
Legacy Models
Gigapixel's Generation v1 AI Models are the original models used in previous versions that are now considered under our Legacy models.
How to find Legacy Models:
Select the three dots next to the Auto Symbol > Show Legacy Models
