Hugging Face's logo

qualcomm
/
First-Order-Motion-Model

Image-to-Video
PyTorch
android
Model card Files
xet
 Community
1
First-Order-Motion-Model / README.md
qaihm-bot's picture
qaihm-bot
v0.60.0
511bd0a verified
preview code
|
Raw
History Blame Contribute Delete
5 kB
metadata 
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. 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.

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 1.27.1 Download

For more device-specific assets and performance metrics, visit First-Order-Motion-Model on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models 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 for usage instructions.

Model Details

Model Type: Model_use_case.video_generation

Model Stats:

  • Input resolution: 256x256
  • Model checkpoint: vox-256
  • 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 3.248 ms 0 - 39 MB NPU
detector ONNX float Snapdragon® 8 Gen 1 Mobile 7.19 ms 1 - 37 MB NPU
detector ONNX float Qualcomm® Dragonwing™ IQ-8275 6.551 ms 1 - 4 MB NPU
detector ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.379 ms 0 - 29 MB NPU
detector ONNX float Qualcomm® QCS8450 7.19 ms 1 - 37 MB NPU
detector ONNX float Qualcomm® Dragonwing™ IQ-9075 5.618 ms 1 - 4 MB NPU
detector ONNX float Qualcomm® Dragonwing™ Q-8750 2.914 ms 0 - 22 MB NPU
detector ONNX float Snapdragon® 8 Elite Mobile 2.914 ms 0 - 22 MB NPU
detector ONNX float Snapdragon® 8 Elite Gen 5 Mobile 2.746 ms 0 - 27 MB NPU
generator ONNX float Snapdragon® 8 Gen 3 Mobile 16.159 ms 20 - 211 MB NPU
generator ONNX float Snapdragon® 8 Gen 1 Mobile 36.979 ms 16 - 205 MB NPU
generator ONNX float Qualcomm® Dragonwing™ IQ-8275 39.104 ms 16 - 20 MB NPU
generator ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 21.818 ms 0 - 98 MB NPU
generator ONNX float Qualcomm® QCS8450 36.979 ms 16 - 205 MB NPU
generator ONNX float Qualcomm® Dragonwing™ IQ-9075 34.375 ms 18 - 22 MB NPU
generator ONNX float Qualcomm® Dragonwing™ Q-8750 13.312 ms 16 - 179 MB NPU
generator ONNX float Snapdragon® 8 Elite Mobile 13.312 ms 16 - 179 MB NPU
generator ONNX float Snapdragon® 8 Elite Gen 5 Mobile 10.647 ms 12 - 184 MB NPU

License

  • The license for the original implementation of First-Order-Motion-Model can be found here.

References

Community