Photo editing

SUPIR

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

The last open version came out in Feb 2024. 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, Shanghai AI Lab and others), China
First release
Feb 2024
Latest release
Feb 2024
Sizes
based on SDXL, plus LLaVA 13B for captions
License
Non-commercial onlyNon-commercial use only (commercial use with the authors' written permission)
Running
On your own serverNeeds a GPU
Industries
Media and production, Science and research
Deploy on your server GitHub

What it does

  • Restoring old and blurry photos
  • Upscaling with detail reconstruction
  • Archive restoration pilots

Where it is used

Media and archivesPhoto studiosMuseums and libraries

Hardware requirements

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

Versions

  1. SUPIR v0Q и v0F

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 SUPIR be used in a commercial project?

No. License: Non-commercial use only (commercial use with the authors' written permission). A commercial product needs a different model or a separate agreement with the rights holder.

What hardware does SUPIR need?

At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does SUPIR support Russian?

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

Where can I download SUPIR and what does it cost?

The SUPIR 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.

Comparisons

Similar models

Photo editingSeedVR / SeedVR2ByteDance Seed · ChinaCommercial use allowed

ByteDance's video and photo restoration and upscaling. SeedVR2 does it in a single step, so it is noticeably faster than similar models. Commercial-friendly license.

DetailsPhoto editingStableSRS-Lab, Nanyang Technological University · SingaporeNon-commercial only

One of the first Stable Diffusion-based photo upscalers: restores realistic details. Non-commercial license.

DetailsPhoto editingFlux.1-dev ControlNet UpscalerJasper AI · USANon-commercial only

A FLUX add-on for upscaling small and blurry images with detail reconstruction. Popular, but under the non-commercial FLUX dev license.

Details

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