| --- |
| library_name: pytorch |
| license: other |
| tags: |
| - android |
| pipeline_tag: image-to-video |
|
|
| --- |
| |
|  |
|
|
| # First-Order-Motion-Model: Optimized for Qualcomm Devices |
|
|
| FOMM is a machine learning model that animates a still image to mirror the movements from a target video. |
|
|
| This is based on the implementation of First-Order-Motion-Model found [here](https://github.com/AliaksandrSiarohin/first-order-model/tree/master). |
| This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/fomm) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary). |
|
|
| Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device. |
|
|
| ## Getting Started |
| There are two ways to deploy this model on your device: |
|
|
| ### Option 1: Download Pre-Exported Models |
|
|
| Below are pre-exported model assets ready for deployment. |
|
|
| | Runtime | Precision | Chipset | SDK Versions | Download | |
| |---|---|---|---|---| |
| | ONNX | float | Universal | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fomm/releases/v0.58.0/fomm-onnx-float.zip) |
|
|
| For more device-specific assets and performance metrics, visit **[First-Order-Motion-Model on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/fomm)**. |
|
|
|
|
| ### Option 2: Export with Custom Configurations |
|
|
| Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/fomm) Python library to compile and export the model with your own: |
| - Custom weights (e.g., fine-tuned checkpoints) |
| - Custom input shapes |
| - Target device and runtime configurations |
|
|
| This option is ideal if you need to customize the model beyond the default configuration provided here. |
|
|
| See our repository for [First-Order-Motion-Model on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/fomm) for usage instructions. |
|
|
| ## Model Details |
|
|
| **Model Type:** Model_use_case.video_generation |
| |
| **Model Stats:** |
| - Model checkpoint: vox-256 |
| - Input resolution: 256x256 |
| - Model size (detector) (float): 54.2 MB |
| - Model size (generator) (float): 174 MB |
| |
| ## Performance Summary |
| | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
| |---|---|---|---|---|---|--- |
| | detector | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 3.249 ms | 1 - 34 MB | NPU |
| | detector | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 7.323 ms | 1 - 36 MB | NPU |
| | detector | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.384 ms | 0 - 154 MB | NPU |
| | detector | ONNX | float | Qualcomm® QCS8450 | 7.323 ms | 1 - 36 MB | NPU |
| | detector | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 5.61 ms | 1 - 4 MB | NPU |
| | detector | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.747 ms | 0 - 25 MB | NPU |
| | detector | ONNX | float | Snapdragon® 8 Elite Mobile | 2.916 ms | 0 - 22 MB | NPU |
| | detector | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 2.916 ms | 0 - 22 MB | NPU |
| | detector | TFLITE | float | Qualcomm® SA8775P | 11.63 ms | 1 - 19 MB | GPU |
| | detector | TFLITE | float | Qualcomm® SA8650P | 11.63 ms | 1 - 19 MB | GPU |
| | detector | TFLITE | float | Qualcomm® SA8255P | 11.63 ms | 1 - 19 MB | GPU |
| | generator | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 16.253 ms | 0 - 191 MB | NPU |
| | generator | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 36.974 ms | 0 - 188 MB | NPU |
| | generator | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 21.835 ms | 18 - 21 MB | NPU |
| | generator | ONNX | float | Qualcomm® QCS8450 | 36.974 ms | 0 - 188 MB | NPU |
| | generator | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 34.288 ms | 16 - 19 MB | NPU |
| | generator | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 11.137 ms | 17 - 188 MB | NPU |
| | generator | ONNX | float | Snapdragon® 8 Elite Mobile | 12.921 ms | 16 - 180 MB | NPU |
| | generator | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 12.921 ms | 16 - 180 MB | NPU |
| | generator | TFLITE | float | Qualcomm® SA8775P | 819.964 ms | 21 - 37 MB | CPU |
| | generator | TFLITE | float | Qualcomm® SA8650P | 819.964 ms | 21 - 37 MB | CPU |
| | generator | TFLITE | float | Qualcomm® SA8255P | 819.964 ms | 21 - 37 MB | CPU |
| |
| ## License |
| * The license for the original implementation of First-Order-Motion-Model can be found |
| [here](https://github.com/AliaksandrSiarohin/first-order-model/blob/master/LICENSE.md). |
| |
| ## References |
| * [First Order Motion Model for Image Animation](https://arxiv.org/abs/2003.00196) |
| * [Source Model Implementation](https://github.com/AliaksandrSiarohin/first-order-model/tree/master) |
| |
| ## Community |
| * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI. |
| * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com). |
| |
