- Saved searches
- Use saved searches to filter your results more quickly
- License
- TimNekk/Gigapixel
- Name already in use
- Sign In Required
- Launching GitHub Desktop
- Launching GitHub Desktop
- Launching Xcode
- Launching Visual Studio Code
- Latest commit
- Git stats
- Files
- README.md
- Exceptional AI image upscaler delivering enhanced detail and resolution by 600%.
- Upscale image resolution instead of just enlarging pixels.
- Improve image quality.
- Recover natural details and textures in low-resolution faces with Face Recovery AI
- Add image detail that looks completely natural.
- Enhance the texture of feathers
- Improve fur texture and sharpness
- Higher-resolution landscapes
- More detailed cityscapes
- Crystal-clear upscaling with no blocky artifacts
- Fix extreme pixellation in low-resolution images
- Create better prints
- Increase DPI by increasing the image’s real resolution
- Remove close-up compression artifacts
- Better zooming and cropping
- Enhance different patterns in fabric and flora
- Natural texture that looks like it was never upscaled
- Other use cases: video, CG, and more
- Remastering Final Fantasy VII
- Upscaling computer game textures
- Star Trek: Deep Space 9 Remastered with ML
- Old footage to 4k
- Easy workflow
- From Adobe Lightroom Classic
- From Adobe Photoshop
- As a standalone
- Get Gigapixel AI
Saved searches
Use saved searches to filter your results more quickly
You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session.
Topaz Gigapixel AI automation tool
License
TimNekk/Gigapixel
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Name already in use
A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
Sign In Required
Please sign in to use Codespaces.
Launching GitHub Desktop
If nothing happens, download GitHub Desktop and try again.
Launching GitHub Desktop
If nothing happens, download GitHub Desktop and try again.
Launching Xcode
If nothing happens, download Xcode and try again.
Launching Visual Studio Code
Your codespace will open once ready.
There was a problem preparing your codespace, please try again.
Latest commit
Git stats
Files
Failed to load latest commit information.
README.md
Topaz Gigapixel AI automation tool
Topaz Gigapixel AI v6.3.3 or newer required
Install the current version with PyPI
from gigapixel import Gigapixel, Scale, Mode, OutputFormat from pathlib import Path # Path to Gigapixel executable file. exe_path = Path('C:\Program Files\Topaz Labs LLC\Topaz Gigapixel AI\Topaz Gigapixel AI.exe') # Output file suffix. (e.g. pic.jpg -> pic-gigapixel.jpg) # You should set same value inside Gigapixel (File -> Preferences -> Default filename suffix). output_suffix = '-gigapixel' # Create Gigapixel instance. app = Gigapixel(exe_path, output_suffix) # Process image. image = Path('path/to/image.jpg') output_path = app.process(image, scale=Scale.X2, mode=Mode.STANDARD, delete_from_history=True, output_format=OutputFormat.PNG) # Print output path. print(output_path)
Bug reports and/or pull requests are welcome
The module is available as open source under the terms of the Apache License, Version 2.0
Exceptional AI image upscaler delivering enhanced detail and resolution by 600%.
Use deep learning to get better photo quality by enhancing detail. Join the hundreds of thousands of photographers and designers who use Gigapixel AI for better printing, cropping, restoration, and more.
Upscale image resolution instead of just enlarging pixels.
Gigapixel AI helps you do a single thing very well: increase image resolution in a natural way. This is pretty hard to do. Most upscaling algorithms don’t know how to accurately fill in missing pixels, so you end up with blocky low-quality results.
To solve this problem, Gigapixel AI’s neural networks are continuously trained on a wide variety of sample images to understand how photorealistic detail looks. After learning from millions of images, our AI image upscaler can now believably increase resolution on a wide variety of different subjects (portraits, wildlife, landscapes, architecture, etc) and image types (DSLR, web/compressed, CG). The results are often magical. Give our intelligent image resolution enhancer a try!
“Gigapixel AI is essentially the ‘ENHANCE!’ meme in real life. It works so well that one of Topaz Labs’ biggest challenges is convincing customers that the examples on its site are real.”
«Using sophisticated neural networks, Gigapixel AI adds realistic details into an image to avoid making it look blurry as it’s scaled up. The result is remarkable.»
– Timothy B. Lee, Ars Technica
«Advances in AI have enabled better upscaling technology than previously available. The most notable tool is Gigapixel AI by Topaz Labs, software that upscales images with staggering results.»
«Topaz Labs’ Gigapixel upscaling doesn’t just look at neighboring pixels; it looks at whole sections of images at a time. That allows it to better re-create larger structures.»
Improve image quality.
Gigapixel AI can make your image appear like it was captured with a much higher-quality camera. It’s been trained on enough images of different types of subjects (like portraits, landscapes, architecture, and more) to know what photo detail should look like. This allows you to increase your photo’s resolution and quality very naturally with minimal artifacts.
Pixel count isn’t the only thing that affects image quality. Normally, if you start out with a low-quality image, you’ll just end up with a bigger low-quality image if you upscale it. Gigapixel AI upscale technology can instead create very believable and natural image detail that can often look amazing.
Download the original versions of these images and try our AI image upscaler for yourself. Enjoy!
“AI upscaling is here. and it’s terrifyingly good. It learns what images should look like, and applies that knowledge to new stuff. It’s super effective.”
Recover natural details and textures in low-resolution faces with Face Recovery AI
The breakthrough technology of Face Recovery AI introduced in Gigapixel AI v6.1 offers remarkable detail enhancement for low-resolution faces. Here you’ll see fine details and textures are accurately created by Face Recovery AI, while simultaneously upscaling by 600%.
Add image detail that looks completely natural.
Normally enlarging an originally low-quality image will cause fuzzy square artifacts that visually degrade the image. Because Gigapixel AI was trained on an extensive dataset of mountain textures (among other subjects), it’s able to enlarge image details while increasing the resolution. You almost can’t tell that an AI upscaler was used.
Enhance the texture of feathers
Feathers are often difficult to enhance correctly; they need to be both sharp and soft in different places to look natural. While this is difficult for normal enlargement methods, Gigapixel AI understands how to increase feather detail in a believable way.
Improve fur texture and sharpness
Fur is another tricky subject due to the ultra-fine details with varying widths and textures. When upscaling animals, Gigapixel AI adds believable fur detail and texture, while maintaining bokeh in appropriate places, for the kinds of results you see above.
Higher-resolution landscapes
Landscapes often look unnatural without fine detail. Gigapixel AI can add believable texture from existing detail and dramatically increase the image quality of your landscapes.
More detailed cityscapes
Man-made architecture often have more straight and clearly-defined lines than nature. Gigapixel’s special “Lines” AI model was trained specifically on architecture and objects for better results.
Crystal-clear upscaling with no blocky artifacts
Normal upscaling techniques will create fuzzy and blocky artifacts that you can see above, but Gigapixel AI resolves edges sharply with few artifacts for much more natural results. (Pay special attention above to the fine details around the windows, trees, and mountain edges.)
Fix extreme pixellation in low-resolution images
While Gigapixel AI works best with input images that start with moderate or high quality, it can also work wonders on extremely low-quality and compressed images. In addition to increasing resolution, the “Very Compressed” model will also automatically remove JPEG compression artifacts, apply noise reduction, and sharpen the output in a natural way.
Sharpen AI has become crucial. Besides improving photos that were already sharp, it can fix photos with slow shutter speed or where it’s slightly out of focus! I honestly cannot imagine going back to editing without it.
Create better prints
Large prints display every small bit of detail in your photo, so it’s especially important that you start with a high-quality image. Gigapixel AI helps you enlarge photo size and achieve the extra image resolution to make your print really pop. In fact, Gigapixel AI works even better when starting out with an already high-quality image, so you can get especially good results here.
«You see a huge difference. there’s just no comparison.»
Increase DPI by increasing the image’s real resolution
Printed photos will often magnify any softness or imperfections in your source image. Upscaling with Gigapixel AI first ensures the most detailed original image for best printing results.
Remove close-up compression artifacts
Compression artifacts often look especially jarring in a printed photo. Gigapixel AI can upscale photo resolution while automatically removing compression artifacts, so you get a clean print every time.
Better zooming and cropping
Even if you use a high-quality camera, zooming into your image will reveal softness and imperfections. Using Gigapixel AI to increase your image’s resolution enables you to zoom and crop without losing quality.
«Gigapixel AI’s done a good job. It’s almost impossible to tell the difference between [high-res vs upscaled].»
Enhance different patterns in fabric and flora
Different kinds of texture have different characteristics. In the image above, notice the added detail and resolution on the fabric and grass when using Gigapixel AI’s image upscaling technology.
Natural texture that looks like it was never upscaled
The main statue looks far sharper in the photo above, but pay special attention to the people around the bottom. The resolution of the photo has increased even with no additional image information.
Other use cases: video, CG, and more
While Gigapixel AI was mostly trained for photorealistic still images (aside from the CG model), many creators have also achieved great results with computer graphics and video.
Note: if you’re interested in video enhancement, check out Video Enhance AI as well!
«The original file was really heavily pixellated, and it seems to have cleaned it up a lot.»
Remastering Final Fantasy VII
The Night Sky Prince gives a great video overview of efforts to use Gigapixel AI to remaster old Final Fantasy VII textures. Originally mentioned in PC Gamer “AI Neural Networks are Giving Final Fantasy 7 a Makeover”.
Upscaling computer game textures
3kliksphilip uses Gigapixel AI to upscale Counter-Strike 1.6 map textures and shows the difference.
Star Trek: Deep Space 9 Remastered with ML
CaptRobau upscales Deep Space 9 to 4K resolution and compares the difference. Read his written tutorial here.
Old footage to 4k
Tutorial from Integnity that uses Gigapixel AI and a few other tools to convert old black and white footage into magical 4k. (Also take a look at Video Enhance AI if you’re interested in this.)
I usually shoot with a large aperture for creamy bokeh, but you can get an image slightly out of focus from time to time. Sharpen AI helps me recover all that detail, pushing the quality of my work to a whole new level.”
I shoot on helicopters and planes, so you can imagine the motion and vibration. I use Sharpen AI on every image I edit. I’ve never experienced such peace of mind knowing my images will come out looking better than before.
Easy workflow
Gigapixel AI works directly on your Mac or PC. Use the standalone to batch process thousands of images in sequence, or use it as a Photoshop plugin for tight workflow integration. We’ve also partnered with major CPU/GPU manufacturers like Nvidia and Intel to make Gigapixel AI run as fast as possible for your computer.
From Adobe Lightroom Classic
Send a single image or multiple ones to Gigapixel AI from Lightroom Classic. Afterwards, your photos will be conveniently stacked on top of your original files in Lightroom Classic for further processing or export.
From Adobe Photoshop
Directly upscale and enhance a layer in Gigapixel AI from Photoshop by launching it as a filter. Your image will be saved back to Photoshop at its new resolution.
As a standalone
Gigapixel AI also works as a standalone product, so you can use it without any other host software. Upscale and enhance multiple images at once.
Double your image quality with Gigapixel AI
– Ben Claremont
Lightroom and Photoshop Workflow with Gigapixel
– Dave Kelly
Topaz Gigapixel AI works!
– Anthony Morganti
Get Gigapixel AI
Use deep learning to get better photo quality by enhancing detail. Join the hundreds of thousands of photographers and designers who use Gigapixel AI for better printing, cropping, restoration, and more.
Includes all platforms
Includes standalone and LR/PS plugins for both Mac and Windows. Re-download and re-install at any time.
Buy once, own forever
You own the version you bought forever. You also get 1 year of new AI models and major upgrades with your purchase.
Live support
Email us, we’ll get back to you within one business day.
30-day refund guarantee
If you don’t like the product or if it doesn’t work for any reason, contact us within 30 days for a no-questions-asked refund.