| | --- |
| | 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/quic/ai-hub-models/blob/main/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 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fomm/releases/v0.46.1/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/quic/ai-hub-models/blob/main/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/quic/ai-hub-models/blob/main/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 (FOMMDetector) (float): 54.2 MB |
| | - Model size (FOMMGenerator) (float): 174 MB |
| | |
| | ## Performance Summary |
| | | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
| | |---|---|---|---|---|---|--- |
| | | FOMMDetector | ONNX | float | Snapdragon® X Elite | 4.668 ms | 28 - 28 MB | NPU |
| | | FOMMDetector | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 3.421 ms | 0 - 104 MB | NPU |
| | | FOMMDetector | ONNX | float | Qualcomm® QCS8550 (Proxy) | 4.575 ms | 0 - 30 MB | NPU |
| | | FOMMDetector | ONNX | float | Qualcomm® QCS9075 | 6.01 ms | 1 - 4 MB | NPU |
| | | FOMMDetector | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.023 ms | 0 - 91 MB | NPU |
| | | FOMMDetector | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.857 ms | 0 - 91 MB | NPU |
| | | FOMMGenerator | ONNX | float | Snapdragon® X Elite | 22.761 ms | 88 - 88 MB | NPU |
| | | FOMMGenerator | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 16.694 ms | 0 - 176 MB | NPU |
| | | FOMMGenerator | ONNX | float | Qualcomm® QCS8550 (Proxy) | 23.05 ms | 18 - 21 MB | NPU |
| | | FOMMGenerator | ONNX | float | Qualcomm® QCS9075 | 35.444 ms | 18 - 22 MB | NPU |
| | | FOMMGenerator | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 13.959 ms | 14 - 153 MB | NPU |
| | | FOMMGenerator | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 10.851 ms | 0 - 150 MB | NPU |
| | |
| | ## 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). |
| | |
