Model · Tencent ARC Lab · Image-Enhance
Real-ESRGAN
The de-facto open-weights image upscaler. Battle-tested across years of community use; runs on CPU or GPU, integrates with virtually every local image pipeline.
- Modality
- Image-Enhance
- License
- BSD-3-Clause (Open)
- Released
- July 22, 2021
- Last verified
- October 28, 2026
- Runs locally
- Yes
What you need to run it
- Mac
- Yes. Any Apple Silicon Mac (M1 or newer) with at least 8 GB (16 GB recommended) of memory. Newer chips are faster, but memory is what decides whether it runs.
- Windows / Linux PC
- NVIDIA works best. A graphics card with at least 4 GB (6 GB recommended) of video memory.
- No graphics card
- Works. Runs on a normal computer's processor, just slower.
A ready-made macOS app (ncnn-vulkan) runs it on Apple chips; very large images need more memory and time.
Numbers are for: RealESRGAN x4plus (ncnn-vulkan app or PyTorch). Our estimate from the model’s size — the maker publishes no figure.
Strengths
- Permissive BSD license — fully open commercially
- Decade of community tooling — ComfyUI nodes, Automatic1111, CLI wrappers
- Specialised variants for anime, faces, and general photos
Weaknesses
- Older architecture — diffusion-based upscalers can produce more detail
- Default models can over-smooth on photographic textures
- Repo dormant: no commits since April 2024 and no pushes since August 2024 — for more detail, the newer SeedVR2 (Apache 2.0) restores and upscales in one diffusion step
Try it
| Where | Type | Notes |
|---|---|---|
| GitHub | local | Reference implementation |
| Hugging Face | weights | Pre-trained weights |
| Replicate | hosted | API key required |
| Upscayl | local | Free no-code desktop app (AGPL-3.0) for Windows, macOS and Linux; needs a Vulkan-capable GPU |
Official sources
Change log
- — Added hardware requirements (Mac support, memory, NVIDIA). Source: estimate from size and community builds (github xinntao/Real-ESRGAN README (ncnn-vulkan portable builds)).
- — Still current, not deprecated: the repo is dormant (last commit 2024-04, last push 2024-08) but Real-ESRGAN is still the engine inside Upscayl (51.2k GitHub stars, AGPL-3.0), the popular free desktop upscaler, added as a provider. Newer option for higher detail: SeedVR2.
- — Verified current and not archived; last release v0.3.0 (2022-09-20). No successor exists — the README's GFPGAN/BasicSR links are complementary projects, not replacements. Canonical repo remains under the author's personal account; TencentARC/Real-ESRGAN returns 404.
- — Initial entry.
Esc