Model reference · open weights
ESRGAN 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 | 970 downloads / month |
| Licence | Open weights |
About
ESRGAN is a machine learning model that upscales an image with minimal loss in quality.
This is based on the implementation of ESRGAN 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 | w8a16 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| QNN_DLC | float | Universal | QAIRT 2.45 | Download |
| QNN_DLC | w8a16 | Universal | QAIRT 2.45 | Download |
| TFLITE | float | Universal | QAIRT 2.45 | Download |
For more device-specific assets and performance metrics, visit ESRGAN 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 ESRGAN 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 |
|---|---|---|---|---|---|---|
| ESRGAN | ONNX | float | Snapdragon® X2 Elite | 34.318 ms | 8 - 8 MB | NPU |
| ESRGAN | ONNX | float | Snapdragon® X Elite | 65.423 ms | 38 - 38 MB | NPU |
| ESRGAN | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 51.062 ms | 0 - 745 MB | NPU |
| ESRGAN | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 118.049 ms | 4 - 741 MB | NPU |
| ESRGAN | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 127.563 ms | 6 - 10 MB | NPU |
| ESRGAN | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 63.529 ms | 0 - 43 MB | NPU |
| ESRGAN | ONNX | float | Qualcomm® QCS8450 | 118.049 ms | 4 - 741 MB | NPU |
| ESRGAN | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 105.926 ms | 6 - 9 MB | NPU |
| ESRGAN | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 65.423 ms | 38 - 38 MB | NPU |
| ESRGAN | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 38.69 ms | 7 - 358 MB | NPU |
| ESRGAN | ONNX | float | Snapdragon® 8 Elite Mobile | 38.69 ms | 7 - 358 MB | NPU |
| ESRGAN | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 26.12 ms | 5 - 361 MB | NPU |
| ESRGAN | ONNX | w8a16 | Snapdragon® X2 Elite | 21.996 ms | 4 - 4 MB | NPU |
| ESRGAN | ONNX | w8a16 | Snapdragon® X Elite | 43.397 ms | 26 - 26 MB | NPU |
| ESRGAN | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 31.981 ms | 3 - 1115 MB | NPU |
| ESRGAN | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 83.95 ms | 4 - 1198 MB | NPU |
| ESRGAN | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 323.654 ms | 4 - 7 MB | NPU |
| ESRGAN | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 43.191 ms | 3 - 7 MB | NPU |
| ESRGAN | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 41.903 ms | 0 - 725 MB | NPU |
| ESRGAN | ONNX | w8a16 | Qualcomm® QCS8450 | 83.95 ms | 4 - 1198 MB | NPU |
| ESRGAN | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 38.006 ms | 3 - 6 MB | NPU |
| ESRGAN | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 43.397 ms | 26 - 26 MB | NPU |
| ESRGAN | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 1128.366 ms | 0 - 696 MB | NPU |
| ESRGAN | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 89.102 ms | 3 - 784 MB | NPU |
| ESRGAN | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 26.489 ms | 3 - 907 MB | NPU |
| ESRGAN | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 26.489 ms | 3 - 907 MB | NPU |
| ESRGAN | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 16.934 ms | 3 - 1072 MB | NPU |
| ESRGAN | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 89.102 ms | 3 - 784 MB | NPU |
| ESRGAN | QNN_DLC | float | Snapdragon® X2 Elite | 34.371 ms | 0 - 0 MB | NPU |
| ESRGAN | QNN_DLC | float | Snapdragon® X Elite | 65.02 ms | 0 - 0 MB | NPU |
| ESRGAN | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 48.702 ms | 0 - 706 MB | NPU |
| ESRGAN | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 112.305 ms | 0 - 709 MB | NPU |
| ESRGAN | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 127.079 ms | 0 - 6 MB | NPU |
| ESRGAN | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 62.121 ms | 0 - 4 MB | NPU |
| ESRGAN |
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 esrgan for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (esrgan 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":"esrgan","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.