Creative vision doesn’t come in standard definition. The nine AI-powered tools in Topaz Gigapixel not only make your images larger, but more detailed, more real, and even more valuable.

The industry standard for upscaling.
Used by professional photographers, fine artists, designers, illustrators, and creative teams worldwide. Gigapixel AI was the first commercially available AI image upscaler, since 2019. Now as Topaz Gigapixel, the models are better than ever.

6x Lossless Zoom
Crop in on your subject without losing quality and while enhancing detail.

True-to-Input Details
Explore nine different AI models inside Topaz Gigapixel to make every image larger.

Use Before Every Print
From poster to billboard. Ensure every detail is crisp, defined, and bold.

Photogs, Artists & Designers
Every type of creative professional can benefit from running their images through Topaz Gigapixel.

System Requirements:
Windows Operating System: 10 or 11 (most updated version recommended)
System Memory (RAM): 16GB
CPU: Intel or AMD, with AVX instructions, released after 2013
GPU: NVIDIA GTX 980 Ti | 6GB VRAM | AMD Radeon 570 | 6GB VRAM | Intel UHD 600 Graphics | 16GB RAM

On GPUs that meet the minimum VRAM requirements (8GB and 12GB cards) NeuroServer was running inefficently due to memory usage. We have reduced requirements to allow faster image processing on these devices which were bottlenecked by memory. For 8GB and 12GB VRAM GPUs, the speed improvement is up to 4x.

in our testing with an NVIDIA 4060 Laptop GPU with 8GB VRAM, we upscaled a 24MP image to 96MP (2x upscale) with the following results. Note that devices with more GPU have lower improvement due to no memory bottleneck in processing.

• 1982s (33m) processing time on v1.6.0
• 450s (7.5m) processing time on v1.6.1, a 4x increase

If you’ve been avoiding these models for larger images or batches because of processing time, this update changes that calculation.

 

Changelog version 1.3.2:

• Update OpenImageIO
  • Fixes various HEIC file related crashes
  • Adds JXL support
• Updated ImageAI
  • Fixed issue with Face Recovery v3 face rendering
• Added support for non-ascii paths in Windows installer
• Updated renewal info dialog to be less confusing
• Fixed Mac installer sometimes getting stuck unpacking Wonder models
• Fixed Windows installer sometimes crashing
• Fixed Windows installer model download timeout handling
• Fixed cloud upload temp files potentially being renamed incorrectly
• Fixed login errors showing on outdated dialog
• Fixed thumbnail generation sometimes crashing
• Fixed app sometimes being unable to merge instances

 

More Info

 

Thanks to Team VR, AlekseyPopovv, 423down and rbc release

Installation may takes a long time to update 2x gb models

 

(Hooked Silent Install Repack) x64 

Download