Ross ROSS = Recommend OSS · open-source software intelligence for agents

Real-ESRGAN

Some data may be outdated — see provenance labels.

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration. observed · 2026-10-03

github.com/xinntao/Real-ESRGAN · Python · BSD-3-Clause (permissive) observed · 2026-10-03

Health v2 · maintenance only

23/100

  • Activity 0
  • Release rhythm 8
  • Longevity 100
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-21. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 1920
  • days_rel: n/a
  • days_push: 805
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

36970 stars · 4488 forks observed · 2026-10-03

What it is AI-extracted, prompt v1, taxonomy v1, 2026-09-28, confidence 0.98

Real-ESRGAN is a Python library that provides state‑of‑the‑art models for image and video super‑resolution and restoration. It includes pretrained models for general photos, anime, and video, and offers both a pip package and portable executables for GPU acceleration.

Use cases

  • enhance low‑resolution photos to high‑resolution quality
  • restore details in compressed JPEG images
  • upscale anime artwork while preserving line art and colors
  • improve video frames for smoother playback
  • denoise noisy images captured in low light
  • prepare images for printing or large‑format displays

When to choose

  • You need a high‑quality, open‑source solution for image or video upscaling.
  • You work with anime or cartoon graphics and want specialized models.
  • You prefer a library with both Python API and ready‑to‑run GPU executables.
  • You require a model that handles JPEG compression artifacts and noise.

When to avoid

  • You need real‑time upscaling on low‑end hardware without GPU support.
  • Your workflow is limited to pure CPU environments and cannot install CUDA or Vulkan dependencies.
  • You require a commercial‑grade warranty or dedicated support.

Facets

library · maturity active

image-processing video-processing computer-vision python windows super-resolution real-esrgan anime denoise jpeg-compression ncnn-vulkan linux macos

2 sources

Member repositories

RepositoryRoleHealth v2
xinntao/Real-ESRGANmain23
xinntao/Real-ESRGAN-ncnn-vulkansdk23

For agents

markdown · JSON · MCP: product_card(name="xinntao/Real-ESRGAN")

Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem