Model reference · open weights
LaMa-Dilated 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
LaMa-Dilated is a machine learning model that allows to erase and in-paint part of given input image.
This is based on the implementation of LaMa-Dilated 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 |
| QNN_DLC | float | Universal | QAIRT 2.45 | Download |
| TFLITE | float | Universal | QAIRT 2.45 | Download |
For more device-specific assets and performance metrics, visit LaMa-Dilated 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 LaMa-Dilated on GitHub for usage instructions.
Model Type: Model_use_case.image_editing
Model Stats:
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| LaMa-Dilated | ONNX | float | Snapdragon® X2 Elite | 36.378 ms | 8 - 8 MB | NPU |
| LaMa-Dilated | ONNX | float | Snapdragon® X Elite | 77.556 ms | 90 - 90 MB | NPU |
| LaMa-Dilated | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 54.56 ms | 0 - 479 MB | NPU |
| LaMa-Dilated | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 133.618 ms | 2 - 527 MB | NPU |
| LaMa-Dilated | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 123.774 ms | 6 - 14 MB | NPU |
| LaMa-Dilated | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 77.985 ms | 0 - 94 MB | NPU |
| LaMa-Dilated | ONNX | float | Qualcomm® QCS8450 | 133.618 ms | 2 - 527 MB | NPU |
| LaMa-Dilated | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 108.956 ms | 6 - 13 MB | NPU |
| LaMa-Dilated | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 77.556 ms | 90 - 90 MB | NPU |
| LaMa-Dilated | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 43.695 ms | 7 - 437 MB | NPU |
| LaMa-Dilated | ONNX | float | Snapdragon® 8 Elite Mobile | 43.695 ms | 7 - 437 MB | NPU |
| LaMa-Dilated | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 34.287 ms | 5 - 404 MB | NPU |
| LaMa-Dilated | QNN_DLC | float | Snapdragon® X2 Elite | 34.369 ms | 4 - 4 MB | NPU |
| LaMa-Dilated | QNN_DLC | float | Snapdragon® X Elite | 75.421 ms | 4 - 4 MB | NPU |
| LaMa-Dilated | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 52.33 ms | 0 - 454 MB | NPU |
| LaMa-Dilated | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 133.148 ms | 4 - 409 MB | NPU |
| LaMa-Dilated | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 120.514 ms | 4 - 13 MB | NPU |
| LaMa-Dilated | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 74.969 ms | 4 - 6 MB | NPU |
| LaMa-Dilated | QNN_DLC | float | Qualcomm® SA8775P | 106.893 ms | 1 - 364 MB | NPU |
| LaMa-Dilated | QNN_DLC | float | Qualcomm® SA8650P | 106.893 ms | 1 - 364 MB | NPU |
| LaMa-Dilated | QNN_DLC | float | Qualcomm® SA8255P | 106.893 ms | 1 - 364 MB | NPU |
| LaMa-Dilated | QNN_DLC | float | Qualcomm® QCS8450 | 133.148 ms | 4 - 409 MB | NPU |
| LaMa-Dilated | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 106.306 ms | 4 - 13 MB | NPU |
| LaMa-Dilated | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 75.421 ms | 4 - 4 MB | NPU |
| LaMa-Dilated | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 40.187 ms | 1 - 367 MB | NPU |
| LaMa-Dilated | QNN_DLC | float | Qualcomm® SA7255P | 403.099 ms | 1 - 364 MB | NPU |
| LaMa-Dilated | QNN_DLC | float | Qualcomm® SA8295P | 109.591 ms | 1 - 300 MB | NPU |
| LaMa-Dilated | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 40.187 ms | 1 - 367 MB | NPU |
| LaMa-Dilated | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 32.351 ms | 4 - 397 MB | NPU |
| LaMa-Dilated | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 52.831 ms | 2 - 538 MB | NPU |
| LaMa-Dilated | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 133.005 ms | 4 - 462 MB | NPU |
| LaMa-Dilated | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 121.318 ms | 3 - 106 MB | NPU |
| LaMa-Dilated | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 74.971 ms | 1 - 293 MB | NPU |
| LaMa-Dilated | TFLITE | float | Qualcomm® SA8775P | 106.491 ms | 3 - 380 MB | NPU |
| LaMa-Dilated | TFLITE | float | Qualcomm® SA8650P | 106.491 ms | 3 - 380 MB | NPU |
|
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 lama-dilated for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (lama-dilated 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":"lama-dilated","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.