ModelListedExternal

Real ESRGAN OpenVINO

Pre-converted Real-ESRGAN models in OpenVINO IR format, optimized for Intel CPUs.

Sourcehuggingface.co/ibrhr/Real-ESRGAN-OpenVINO/tree/526cd1817ead9c0f2df99ba1560f2d0e3cc1b487

KindOtherVersionReal esrgan x2plus fp32Bgrade

Model source

Kind: Other
File size: 8.52–31.9 MB
Version: vReal esrgan x2plus fp32
Updated: Oct 9, 2026
Source: Hugging Face

Source description

Real-ESRGAN OpenVINO

Pre-converted Real-ESRGAN models in OpenVINO IR format, optimized for Intel CPUs.

Up to 13x faster than PyTorch for the same accuracy while using less memory.

Models

Model	Scale	Parameters	Use Case
`real_esrgan_x4plus_fp32`	4x	16.7M	General photos
`real_esrgan_x2plus_fp32`	2x	16.7M	General photos (2x)
`real_esrgan_x4plus_anime_6B_fp32`	4x	5.9M	Anime/illustrations

All models accept uint8 NHWC input directly (preprocessing baked into IR).

Highly Optimized

This implementation leverages Intel OpenVINO with AVX-512 and AMX instructions for maximum CPU performance. The speedup increases with image size, making it especially efficient for large images.

Benchmark

For reference, here's the time required to upscale images using different implementations:

PyTorch - Standard PyTorch inference
OpenVINO - Optimized for Intel CPUs

x4plus model on Intel Xeon Platinum 8581C

Input Size	Output Size	PyTorch (s)	OpenVINO (s)	Speedup	Memory
128x128	512x512	0.635	0.114	5.58x	9.9 MB
256x256	1024x1024	3.673	0.391	9.39x	39.2 MB
512x512	2048x2048	19.919	1.485	13.42x	57.9 MB
1024x1024	4096x4096	79.385	5.955	13.33x	96.2 MB

x2plus model on Intel Xeon Platinum 8581C

Input Size	Output Size	PyTorch (s)	OpenVINO (s)	Speedup	Memory
128x128	256x256	0.193	0.051	3.81x	2.6 MB
256x256	512x512	0.682	0.111	6.13x	9.9 MB
512x512	1024x1024	3.604	0.405	8.89x	15.2 MB
1024x1024	2048x2048	21.174	1.618	13.09x	26.5 MB

x4plus_anime_6B model on Intel Xeon Platinum 8581C

Input Size	Output Size	PyTorch (s)	OpenVINO (s)	Speedup	Memory
128x128	512x512	0.243	0.047	5.15x	6.9 MB
256x256	1024x1024	1.287	0.154	8.35x	27.2 MB
512x512	2048x2048	6.617	0.583	11.34x	45.9 MB
1024x1024	4096x4096	26.366	2.341	11.26x	84.2 MB

Benchmarks executed on Intel Xeon Platinum 8581C (8 cores, 16 threads, AVX-512, AMX).

Usage

See the GitHub repository for usage instructions, examples, and benchmarks.

Citations

@inproceedings{wang2021realesrgan,
  title={Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data},
  author={Wang, Xintao and Xie, Liangbin and Dong, Chao and Shan, Ying},
  booktitle={International Conference on Computer Vision Workshops (ICCVW)},
  year={2021}
}

Sources

1 source

Hugging FacePrimaryVersion 526cd1817ead9c0f2df99ba1560f2d0e3cc1b487

huggingface.co/ibrhr/Real-ESRGAN-OpenVINO/tree/526cd1817ead9c0f2df99ba1560f2d0e3cc1b487

Verified Oct 9

Model artifacts

3 artifacts

models/real_esrgan_x2plus_fp32.bin

bin · 31.9 MB · SHA-256 fde9317eb936…a986 · Hugging Face

Download

models/real_esrgan_x4plus_anime_6B_fp32.bin

bin · 8.52 MB · SHA-256 33cdab2f6e29…8a2f · Hugging Face

Download

models/real_esrgan_x4plus_fp32.bin

bin · 31.9 MB · SHA-256 f769a0334272…9c9a · Hugging Face

Download

Source excerpts

2 excerpts

ReadmeJul 31huggingface.co/ibrhr/Real-ESRGAN-OpenVINO

--- license: apache-2.0 tags: - openvino - image-to-image - super-resolution - image-upscaling - real-esrgan base_model: - xinntao/RealESRGAN_x4plus - xinntao/RealESRGAN_x2plus - xinntao/RealESRGAN_x4plus_anime_6B pipeline_tag: image-to-image --- # Real-ESRGAN OpenVINO Pre-converted [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN) models in OpenVINO IR format, optimized for Intel CPUs. **Up to 13x faster** than PyTorch for the same accuracy while using less memory. ## Models | Model | Scale | Parameters | Use Case | |-------|-------|------------|----------| | `real_esrgan_x4plus_fp32` | 4x | 16.7M | General photos | | `real_esrgan_x2plus_fp32` | 2x | 16.7M | General photos (2x) | | `real_esrgan_x4plus_anime_6B_fp32` | 4x | 5.9M | Anime/illustrations | All models accept `uint8` NHWC input directly (preprocessing baked into IR). ## Highly Optimized This implementation leverages Intel OpenVINO with AVX-512 and AMX instructions for maximum CPU performance. The speedup increases with image size, making it especially efficient for large images. ### Benchmark For reference, here's the time required to upscale images using different implementations: * [PyTorch](https://pytorch.org/) - Standard PyTorch inference * [OpenVINO](https://docs.openvino.ai/) - Optimized for Intel CPUs ### x4plus model on Intel Xeon Platinum 8581C | Input Size | Output Size | PyTorch (s) | OpenVINO (s) | Speedup | Memory | |------------|-------------|-------------|--------------|---------|--------| | 128x128 | 512x512 | 0.635 | 0.114 | **5.58x** | 9.9 MB | | 256x256 | 1024x1024 | 3.673 | 0.391 | **9.39x** | 39.2 MB | | 512x512 | 2048x2048 | 19.919 | 1.485 | **13.42x** | 57.9 MB | | 1024x1024 | 4096x4096 | 79.385 | 5.955 | **13.33x** | 96.2 MB | ### x2plus model on Intel Xeon Platinum 8581C | Input Size | Output Size | PyTorch (s) | OpenVINO (s) | Speedup | Memory | |------------|-------------|-------------|--------------|---------|--------| | 128x128 | 256x256 | 0.193 | 0.051 | **3.81x** | 2.6 MB | | 256x256 | 512x512 | 0.682 | 0.111 | **6.13x** | 9.9 MB | | 512x512 | 1024x1024 | 3.604 | 0.405 | **8.89x** | 15.2 MB | | 1024x1024 | 2048x2048 | 21.174 | 1.618 | **13.09x** | 26.5 MB | ### x4plus_anime_6B model on Intel Xeon Platinum 8581C | Input Size | Output Size | PyTorch (s) | OpenVINO (s) | Speedup | Memory | |------------|-------------|-------------|------...

NoteJul 31huggingface.co/ibrhr/Real-ESRGAN-OpenVINO

Source context: 0 downloads · 0 likes · Pipeline image-to-image · Repo ibrhr/Real-ESRGAN-OpenVINO