Model reference · open weights
Real-ESRGAN-x4plus is an open-weight image model from qualcomm. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | qualcomm |
|---|---|
| Type | Image models |
| Task | Image edit |
| Runs with | pytorch |
| Released | 2024-02-25 |
| Popularity | 1k downloads / month |
| Licence | Open weights |
About
Real-ESRGAN is a machine learning model that upscales an image with minimal loss in quality. The implementation is a derivative of the Real-ESRGAN-x4plus architecture, a larger and more powerful version compared to the Real-ESRGAN-general-x4v3 architecture.
This is based on the implementation of Real-ESRGAN-x4plus found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.
Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.
There are two ways to deploy this model on your device:
Below are pre-exported model assets ready for deployment.
| Runtime | Precision | Chipset | SDK Versions | Download |
|---|---|---|---|---|
| ONNX | float | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| ONNX | w8a8 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| QNN_DLC | float | Universal | QAIRT 2.45 | Download |
| QNN_DLC | w8a8 | Universal | QAIRT 2.45 | Download |
| TFLITE | float | Universal | QAIRT 2.45 | Download |
| TFLITE | w8a8 | Universal | QAIRT 2.45 | Download |
For more device-specific assets and performance metrics, visit Real-ESRGAN-x4plus on Qualcomm® AI Hub.
Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:
This option is ideal if you need to customize the model beyond the default configuration provided here.
See our repository for Real-ESRGAN-x4plus on GitHub for usage instructions.
Model Type: Model_use_case.super_resolution
Model Stats:
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| Real-ESRGAN-x4plus | ONNX | float | Snapdragon® X2 Elite | 34.535 ms | 8 - 8 MB | NPU |
| Real-ESRGAN-x4plus | ONNX | float | Snapdragon® X Elite | 65.478 ms | 37 - 37 MB | NPU |
| Real-ESRGAN-x4plus | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 50.898 ms | 0 - 743 MB | NPU |
| Real-ESRGAN-x4plus | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 142.871 ms | 4 - 739 MB | NPU |
| Real-ESRGAN-x4plus | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 127.753 ms | 6 - 10 MB | NPU |
| Real-ESRGAN-x4plus | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 69.852 ms | 0 - 44 MB | NPU |
| Real-ESRGAN-x4plus | ONNX | float | Qualcomm® QCS8450 | 142.871 ms | 4 - 739 MB | NPU |
| Real-ESRGAN-x4plus | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 105.978 ms | 6 - 9 MB | NPU |
| Real-ESRGAN-x4plus | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 65.478 ms | 37 - 37 MB | NPU |
| Real-ESRGAN-x4plus | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 38.121 ms | 7 - 361 MB | NPU |
| Real-ESRGAN-x4plus | ONNX | float | Snapdragon® 8 Elite Mobile | 38.121 ms | 7 - 361 MB | NPU |
| Real-ESRGAN-x4plus | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 26.619 ms | 5 - 361 MB | NPU |
| Real-ESRGAN-x4plus | ONNX | w8a8 | Snapdragon® X2 Elite | 10.228 ms | 3 - 3 MB | NPU |
| Real-ESRGAN-x4plus | ONNX | w8a8 | Snapdragon® X Elite | 25.116 ms | 22 - 22 MB | NPU |
| Real-ESRGAN-x4plus | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 16.475 ms | 2 - 759 MB | NPU |
| Real-ESRGAN-x4plus | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 38.123 ms | 2 - 770 MB | NPU |
| Real-ESRGAN-x4plus | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 146.398 ms | 2 - 4 MB | NPU |
| Real-ESRGAN-x4plus | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 22.822 ms | 2 - 5 MB | NPU |
| Real-ESRGAN-x4plus | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 23.854 ms | 0 - 29 MB | NPU |
| Real-ESRGAN-x4plus | ONNX | w8a8 | Qualcomm® QCS8450 | 38.123 ms | 2 - 770 MB | NPU |
| Real-ESRGAN-x4plus | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 22.533 ms | 2 - 4 MB | NPU |
| Real-ESRGAN-x4plus | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 25.116 ms | 22 - 22 MB | NPU |
| Real-ESRGAN-x4plus | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 468.801 ms | 1 - 506 MB | NPU |
| Real-ESRGAN-x4plus | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 38.237 |
From the published model card. Full card on the HuggingFace links in the sidebar.
How it works
Using it via the API
Once AxForge deploys real-esrgan-x4plus for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (real-esrgan-x4plus below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/images/generations \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"real-esrgan-x4plus","prompt":"a red bicycle","size":"1024x1024"}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.