basicsr
Open Source Image and Video Super-Resolution Toolbox
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires PyTorch and system-level dependencies (CUDA toolkit, C++ compiler); see docs/INSTALL.md for full setup instructions.
- 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 · maintenance · safety
Apache License 2.0 (permissive) — 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.
last release 2022-08-30 (1445 days) · last repo commit 2024-07-21 · 8,367 stars
2 known vulnerabilities (OSV.dev, 2026-08-14) · 289,549 downloads/mo, #8,000 on PyPI
Alternatives
Verify before relying
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)- 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.
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 on this page. Verify before relying on it.
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
basicsr on PyPI
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.
Requires PyTorch and system-level dependencies (CUDA toolkit, C++ compiler); see docs/INSTALL.md for full setup instructions.
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)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 | Not specified |
| Install friction | High. Source build required |
| Runtime dependencies | None |
| Maintenance | Dormant 1,445 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 289,549 / month, #8,000 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | 2 GHSA-86w8-vhw6-q9qq, PYSEC-2026-1215 |
| Classifiers | Development Status :: 4 - BetaLicense :: OSI Approved :: Apache Software LicenseOperating System :: OS IndependentProgramming Language :: Python :: 3Programming Language :: Python :: 3.7Programming Language :: Python :: 3.8 |
Evidence: basicsr-1.4.2.tar.gz
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “image super resolution”
- basicsrBasicSR is a PyTorch-based toolbox for image and video restoration…
- torchsrProvides pretrained neural network models for image super-resolution…
- piexifPiexif reads, writes, and manipulates EXIF metadata in JPEG and WebP…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also realesrgan · torchsr · gfpgan · simple-lama-inpainting · resize-right · facexlib · pytorchcv · speechbrain · torch-model-archiver · fvcore