---
id: basicsr
version: "1.4.2"
license: Apache License 2.0
license_treatment: permissive
maintenance: dormant
---

# basicsr — Open Source Image and Video Super-Resolution Toolbox

License: permissive · Maintenance: dormant · Downloads: 289.5K/mo

## What it is and what it does

BasicSR is an open-source restoration framework built on PyTorch that provides training and inference pipelines for image and video enhancement. It implements multiple architectures for super-resolution, denoising, deblurring, and JPEG artifact removal. The toolbox is designed for researchers and practitioners working on restoration tasks, offering both high-level APIs for quick inference and lower-level components for custom model development.

The package has no runtime dependencies listed, meaning it expects users to install PyTorch and other heavy dependencies separately. This design choice reduces bloat but increases setup complexity. The project is dormant—last released in August 2022 with minimal recent maintenance—so it functions primarily as a reference implementation and code repository rather than an actively maintained library. Two known security vulnerabilities are present in the codebase.

Use it for:

- Train and evaluate super-resolution models on custom datasets using provided pipelines.
- Perform batch inference on images or video frames using pre-trained restoration models.
- Implement custom restoration architectures by extending BasicSR's base classes.
- Benchmark different restoration algorithms on standard datasets.
- Integrate restoration models into production pipelines via the Python API.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

BasicSR is a PyTorch-based toolbox for image and video restoration tasks including super-resolution, denoising, deblurring, and JPEG artifact removal.

Yes, with conditions. BasicSR is worth installing if you need a reference implementation for restoration research or want to train custom models using its provided architectures and pipelines. However, expect high setup friction, no active maintenance, and unresolved security vulnerabilities. For production use, consider sister projects which may offer more stability. Install only if you have PyTorch expertise and can manage dependencies yourself.

## Install

pip install basicsr
uv add basicsr
poetry add basicsr

## Installing basicsr

Before you install: Installation friction is high due to compiled dependencies and complex setup requirements. The project is dormant (last release August 2022, last commit July 2024), so maintenance is minimal; expect no active support for new issues or dependency updates.

License in practice: Released under Apache License 2.0 (permissive), allowing commercial and private use with minimal restrictions, though you must include a copy of the license and state significant changes.

Quickstart:

pip install basicsr

from basicsr.archs.rrdbnet_arch import RRDBNet
from basicsr.upsampler import RealESRGANer

model = RRDBNet(num_in_ch=3, num_out_ch=3)
upsampler = RealESRGANer(scale=4, model_path='model.pth', model=model)

Requires PyTorch and system-level dependencies (CUDA toolkit, C++ compiler); see docs/INSTALL.md for full setup instructions.

Verify before relying:

- Whether pre-trained model weights are bundled or must be downloaded separately.
- Current compatibility with Python 3.9+ (classifiers list only 3.7 and 3.8).
- Specific nature and severity of the two known vulnerabilities (GHSA-86w8-vhw6-q9qq, PYSEC-2026-1215).
- Whether the high install friction is primarily due to PyTorch or additional system dependencies.

## Package facts

- License: Apache License 2.0 (permissive)
- Python support: unspecified
- Install friction: high
- Maintenance: dormant
- Downloads: 289.5K/month (top 15,000 on PyPI)
- Known vulnerabilities: 2

## Tags

image super resolution, video restoration pytorch, image denoising deblurring, JPEG artifact removal, deep learning restoration toolbox, computer vision restoration, neural network image enhancement, image-restoration, video-enhancement, deep-learning

[View on SkillFed](https://skillfed.io/packages/basicsr) · [View on PyPI](https://pypi.org/project/basicsr/)