Photo editing

Real-ESRGAN

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

The last open version came out in Apr 2022. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.

Developer
Tencent ARC Lab, China
First release
Jul 2021
Latest release
Apr 2022
Sizes
about 17M
License
Commercial use allowedBSD-3-Clause
Ready-made builds
GGUF
Running
On your own serverAlso runs without a GPU
Industries
Retail and marketplaces, Media and production
Deploy on your server GitHub

What it does

  • Upscaling old and small product photos
  • Cleaning images of compression artifacts
  • Preparing images for print

Where it is used

Online retailPrintingMedia 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
no versions
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. realesr-general-x4v3 и AnimeVideo-v3
  2. Real-ESRGAN anime 6B
  3. Real-ESRGAN x4plus

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. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can Real-ESRGAN be used in a commercial project?

Yes. License: BSD-3-Clause. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Real-ESRGAN 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 Real-ESRGAN support Russian?

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

Where can I download Real-ESRGAN and what does it cost?

The Real-ESRGAN 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 editingHATXPixel Group (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, and others) · ChinaCommercial use allowed

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

DetailsPhoto 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 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/xinntao/Real-ESRGAN/releases. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.