Real-ESRGAN vs Topaz Gigapixel
Real-ESRGAN
github.comTopaz Gigapixel
topazlabs.comSide by side
| Figure | Real-ESRGAN | Topaz Gigapixel |
|---|---|---|
| Price from | — | $1/mo |
| Free plan | — | — |
| Free trial | — | — |
| Open source | Yes | — |
| Web | Yes | Yes |
| Windows | Yes | Yes |
| macOS | Yes | Yes |
| Linux | Yes | — |
| iOS | — | Yes |
| Android | — | Yes |
| API | — | Yes |
| Self-hosted | Yes | — |
| Plans published | 0 | 12 |
| Spec score · Image Upscaling Software | 8.2 (#33) | 8.9 (#8) |
| Spec score · AI Image Upscalers | 7.6 (#24) | 8.4 (#11) |
| Batch processing | Yes | Batch size is limited by the computer's available resources, with large batches needing more GPU memory and processing power. |
| Desktop app | Yes | Yes |
| Free plan | Yes | No |
| Input formats | The executable accepts JPG, PNG, and WebP images. | JPG/JPEG, PNG, TIF/TIFF, DNG, RAW; HEIF/HEIC, WEBP, PPM, PGM, PBM, PNM |
| Integrations | The README says Real-ESRGAN was integrated into Hugging Face Spaces with Gradio and links to a web demo. | Official plugins are provided for Lightroom Classic and Photoshop; Capture One, Affinity and Apple Photos are not supported plugins. |
| Purpose | Real-ESRGAN develops practical algorithms for general image and video restoration, extending ESRGAN using training with synthetic data. | Topaz Gigapixel is a desktop application that enlarges images and photos while aiming to preserve detail and quality. |
| Support | The README directs questions to the listed email addresses [email protected] and [email protected]. | The product page directs users to Topaz documentation and its support team for product and account help. |
| Upscaling method | ai | ai |
Plans
Topaz Gigapixel
- Personal$29 a month
- Pro$54 a month
- Personal$12 a year
- Personal annual paid monthly$19 a month
- Personal monthly$29 a month
- Topaz Studio$37 a month
- Pro annual paid monthly$54 a month
- Personal annual$149 a year
- Topaz Studio$399 a year
- Topaz Studio$399 a year
In their own words
Real-ESRGAN
Real-ESRGAN is a free, open-source project developing algorithms for image and video restoration. It offers pretrained models for general images, anime images and animation video, including AnimeVideo-v3 and smaller anime models. Image inputs include JPG, PNG and WEBP; inference can handle alpha-channel, grayscale and 16-bit images, and outputs can be JPG, PNG or WebP. Portable inference supports scale ratios of 2, 3 or 4, with 4 as the default; the Python implementation also offers arbitrary output scaling. Portable NCNN executables are available for Windows, Linux and macOS, with required binaries and models included and no CUDA or PyTorch environment needed. These executables do not include every Python feature, including outscale. Python use requires Python 3.7 or newer and PyTorch 1.7 or newer. Online inference is available through an ARC demo and Colab demos. GFPGAN is integrated for face enhancement, and the training code supports fine-tuning on user data or paired data. The project uses synthetic training data and is released under the BSD-3-Clause license.
Topaz Gigapixel
Topaz Gigapixel has no write-up on Specifiction yet; its figures are above.