v0.48.0

See https://github.com/qualcomm/ai-hub-models/releases/v0.48.0 for changelog.

README.md

@@ -14,7 +14,7 @@ pipeline_tag: image-to-video
 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).
+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/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.
 
@@ -27,21 +27,21 @@ Below are pre-exported model assets ready for deployment.
 
 | Runtime | Precision | Chipset | SDK Versions | Download |
 |---|---|---|---|---|
-| ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fomm/releases/v0.47.0/fomm-onnx-float.zip)
+| ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fomm/releases/v0.48.0/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/quic/ai-hub-models/blob/main/qai_hub_models/models/fomm) Python library to compile and export the model with your own:
+Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/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.
+See our repository for [First-Order-Motion-Model on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/fomm) for usage instructions.
 
 ## Model Details
 
@@ -56,20 +56,20 @@ See our repository for [First-Order-Motion-Model on GitHub](https://github.com/q
 ## Performance Summary
 | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
 |---|---|---|---|---|---|---
-| FOMMDetector | ONNX | float | Snapdragon® X Elite | 4.612 ms | 27 - 27 MB | NPU
-| FOMMDetector | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 3.28 ms | 0 - 33 MB | NPU
-| FOMMDetector | ONNX | float | Qualcomm® QCS8550 (Proxy) | 4.37 ms | 1 - 2 MB | NPU
-| FOMMDetector | ONNX | float | Qualcomm® QCS9075 | 5.799 ms | 1 - 4 MB | NPU
-| FOMMDetector | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.928 ms | 0 - 21 MB | NPU
-| FOMMDetector | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.751 ms | 1 - 25 MB | NPU
-| FOMMDetector | ONNX | float | Snapdragon® X2 Elite | 2.67 ms | 28 - 28 MB | NPU
-| FOMMGenerator | ONNX | float | Snapdragon® X Elite | 32.027 ms | 89 - 89 MB | NPU
-| FOMMGenerator | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 17.22 ms | 17 - 241 MB | NPU
-| FOMMGenerator | ONNX | float | Qualcomm® QCS8550 (Proxy) | 22.706 ms | 16 - 18 MB | NPU
-| FOMMGenerator | ONNX | float | Qualcomm® QCS9075 | 34.613 ms | 17 - 21 MB | NPU
-| FOMMGenerator | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 13.711 ms | 13 - 202 MB | NPU
-| FOMMGenerator | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 10.786 ms | 0 - 196 MB | NPU
-| FOMMGenerator | ONNX | float | Snapdragon® X2 Elite | 12.552 ms | 91 - 91 MB | NPU
+| FOMMDetector | ONNX | float | Snapdragon® X2 Elite | 2.661 ms | 28 - 28 MB | NPU
+| FOMMDetector | ONNX | float | Snapdragon® X Elite | 4.614 ms | 27 - 27 MB | NPU
+| FOMMDetector | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 3.294 ms | 0 - 37 MB | NPU
+| FOMMDetector | ONNX | float | Qualcomm® QCS8550 (Proxy) | 4.362 ms | 0 - 22 MB | NPU
+| FOMMDetector | ONNX | float | Qualcomm® QCS9075 | 5.802 ms | 1 - 4 MB | NPU
+| FOMMDetector | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.95 ms | 0 - 27 MB | NPU
+| FOMMDetector | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.75 ms | 0 - 24 MB | NPU
+| FOMMGenerator | ONNX | float | Snapdragon® X2 Elite | 12.37 ms | 91 - 91 MB | NPU
+| FOMMGenerator | ONNX | float | Snapdragon® X Elite | 29.88 ms | 89 - 89 MB | NPU
+| FOMMGenerator | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 17.142 ms | 3 - 223 MB | NPU
+| FOMMGenerator | ONNX | float | Qualcomm® QCS8550 (Proxy) | 22.728 ms | 13 - 24 MB | NPU
+| FOMMGenerator | ONNX | float | Qualcomm® QCS9075 | 35.154 ms | 16 - 19 MB | NPU
+| FOMMGenerator | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 13.631 ms | 17 - 205 MB | NPU
+| FOMMGenerator | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 10.849 ms | 0 - 195 MB | NPU
 
 ## License
 * The license for the original implementation of First-Order-Motion-Model can be found