Photo editing

HAT

Transformer-based photo upscaling, more accurate than SwinIR on fine details. Versions for real noisy photos and a lightweight HAT-S.

The last open version came out in Aug 2023. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.

Developer
XPixel Group (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, and others), China
First release
May 2022
Latest release
Aug 2023
Sizes
9M – 40M
License
Commercial use allowedApache 2.0
Running
On your own serverAlso runs without a GPU
Industries
Media and production, Retail and marketplaces
Deploy on your server GitHub

What it does

  • Upscaling product and interior photos
  • Preparing images for print
  • Sharpening archival photos

Where it is used

PrintingOnline retailMedia and archives

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Real HAT GAN sharper
  2. HAT-S
  3. Real HAT GAN
  4. HAT

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can HAT be used in a commercial project?

Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does HAT need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does HAT support Russian?

Language does not matter for this model: it does not work with text.

Where can I download HAT and what does it cost?

The HAT weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Photo editingSwinIRETH Zurich · SwitzerlandCommercial use allowed

A transformer model for upscaling, denoising and removing JPEG artifacts from photos. Lightweight and proven; often embedded in other systems.

DetailsPhoto editingReal-ESRGANTencent ARC Lab · ChinaCommercial use allowed

The classic for upscaling photos 2–4x while cleaning noise and compression artifacts. Lightweight, runs even on a CPU. Versions for drawings and anime.

DetailsPhoto editingSUPIRXPixel Group (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shanghai AI Lab and others) · ChinaNon-commercial only

Powerful SDXL-based restoration of badly damaged photos: it recreates details rather than just upscaling. Hardware-hungry; non-commercial license.

Details

Source: github.com/XPixelGroup/HAT. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.