Hugging Face's logo

qualcomm
/
First-Order-Motion-Model

Image-to-Video
PyTorch
android
Model card Files
xet
 Community
1
qaihm-bot commited on
Commit
39ec2e5
·
verified ·
1 Parent(s): 0f85312

v0.63.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.63.0 for changelog.

Files changed (2) hide show
  1. README.md +36 -24
  2. release_assets.json +3 -3
README.md CHANGED
@@ -14,7 +14,7 @@ pipeline_tag: image-to-video
14
  FOMM is a machine learning model that animates a still image to mirror the movements from a target video.
15
 
16
  This is based on the implementation of First-Order-Motion-Model found [here](https://github.com/AliaksandrSiarohin/first-order-model/tree/master).
17
- 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/v0.62.2/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).
18
 
19
  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.
20
 
@@ -27,21 +27,21 @@ Below are pre-exported model assets ready for deployment.
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
- | ONNX | float | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fomm/releases/v0.62.2/fomm-onnx-float.zip)
31
 
32
  For more device-specific assets and performance metrics, visit **[First-Order-Motion-Model on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/fomm)**.
33
 
34
 
35
  ### Option 2: Export with Custom Configurations
36
 
37
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.62.2/src/qai_hub_models/models/fomm) Python library to compile and export the model with your own:
38
  - Custom weights (e.g., fine-tuned checkpoints)
39
  - Custom input shapes
40
  - Target device and runtime configurations
41
 
42
  This option is ideal if you need to customize the model beyond the default configuration provided here.
43
 
44
- See our repository for [First-Order-Motion-Model on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.62.2/src/qai_hub_models/models/fomm) for usage instructions.
45
 
46
  ## Model Details
47
 
@@ -56,26 +56,38 @@ See our repository for [First-Order-Motion-Model on GitHub](https://github.com/q
56
  ## Performance Summary
57
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
58
  |---|---|---|---|---|---|---
59
- | detector | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 3.251 ms | 0 - 33 MB | NPU
60
- | detector | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 7.261 ms | 1 - 36 MB | NPU
61
- | detector | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 6.553 ms | 1 - 4 MB | NPU
62
- | detector | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.387 ms | 0 - 29 MB | NPU
63
- | detector | ONNX | float | Qualcomm® QCS8450 | 7.261 ms | 1 - 36 MB | NPU
64
- | detector | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 5.619 ms | 1 - 4 MB | NPU
65
- | detector | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 2.917 ms | 0 - 21 MB | NPU
66
- | detector | ONNX | float | Snapdragon® 8 Elite Mobile | 2.917 ms | 0 - 21 MB | NPU
67
- | detector | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.748 ms | 0 - 26 MB | NPU
68
- | detector | TFLITE | float | Qualcomm® SA7255P | 21.716 ms | 0 - 22 MB | NPU
69
- | generator | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 16.195 ms | 0 - 192 MB | NPU
70
- | generator | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 36.988 ms | 16 - 204 MB | NPU
71
- | generator | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 38.97 ms | 16 - 20 MB | NPU
72
- | generator | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 21.747 ms | 18 - 20 MB | NPU
73
- | generator | ONNX | float | Qualcomm® QCS8450 | 36.988 ms | 16 - 204 MB | NPU
74
- | generator | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 34.741 ms | 18 - 21 MB | NPU
75
- | generator | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 12.914 ms | 13 - 176 MB | NPU
76
- | generator | ONNX | float | Snapdragon® 8 Elite Mobile | 12.914 ms | 13 - 176 MB | NPU
77
- | generator | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 11.013 ms | 16 - 186 MB | NPU
78
- | generator | TFLITE | float | Qualcomm® SA7255P | 2850.009 ms | 21 - 37 MB | CPU
 
 
 
 
 
 
 
 
 
 
 
 
79
 
80
  ## License
81
  * The license for the original implementation of First-Order-Motion-Model can be found
 
14
  FOMM is a machine learning model that animates a still image to mirror the movements from a target video.
15
 
16
  This is based on the implementation of First-Order-Motion-Model found [here](https://github.com/AliaksandrSiarohin/first-order-model/tree/master).
17
+ 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/v0.63.0/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).
18
 
19
  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.
20
 
 
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
+ | ONNX | float | Universal | QAIRT 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fomm/releases/v0.63.0/fomm-onnx-float.zip)
31
 
32
  For more device-specific assets and performance metrics, visit **[First-Order-Motion-Model on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/fomm)**.
33
 
34
 
35
  ### Option 2: Export with Custom Configurations
36
 
37
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/fomm) Python library to compile and export the model with your own:
38
  - Custom weights (e.g., fine-tuned checkpoints)
39
  - Custom input shapes
40
  - Target device and runtime configurations
41
 
42
  This option is ideal if you need to customize the model beyond the default configuration provided here.
43
 
44
+ See our repository for [First-Order-Motion-Model on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/fomm) for usage instructions.
45
 
46
  ## Model Details
47
 
 
56
  ## Performance Summary
57
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
58
  |---|---|---|---|---|---|---
59
+ | detector | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 2.757 ms | 0 - 26 MB | NPU
60
+ | detector | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.902 ms | 0 - 24 MB | NPU
61
+ | detector | ONNX | float | Snapdragon® X2 Elite | 2.664 ms | 2 - 2 MB | NPU
62
+ | detector | ONNX | float | Snapdragon® X Elite | 4.533 ms | 28 - 28 MB | NPU
63
+ | detector | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 3.291 ms | 0 - 36 MB | NPU
64
+ | detector | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 7.375 ms | 1 - 42 MB | NPU
65
+ | detector | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 6.605 ms | 1 - 5 MB | NPU
66
+ | detector | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.42 ms | 0 - 43 MB | NPU
67
+ | detector | ONNX | float | Qualcomm® QCS8450 | 7.375 ms | 1 - 42 MB | NPU
68
+ | detector | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 5.643 ms | 1 - 4 MB | NPU
69
+ | detector | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 4.533 ms | 28 - 28 MB | NPU
70
+ | detector | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 2.902 ms | 0 - 24 MB | NPU
71
+ | detector | TFLITE | float | Qualcomm® SA8775P | 5.807 ms | 0 - 29 MB | NPU
72
+ | detector | TFLITE | float | Qualcomm® SA8650P | 5.807 ms | 0 - 29 MB | NPU
73
+ | detector | TFLITE | float | Qualcomm® SA8255P | 5.807 ms | 0 - 29 MB | NPU
74
+ | detector | TFLITE | float | Qualcomm® SA7255P | 20.3 ms | 0 - 16 MB | GPU
75
+ | generator | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 10.869 ms | 17 - 184 MB | NPU
76
+ | generator | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 13.285 ms | 15 - 170 MB | NPU
77
+ | generator | ONNX | float | Snapdragon® X2 Elite | 12.27 ms | 23 - 23 MB | NPU
78
+ | generator | ONNX | float | Snapdragon® X Elite | 22.403 ms | 89 - 89 MB | NPU
79
+ | generator | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 15.94 ms | 0 - 186 MB | NPU
80
+ | generator | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 35.502 ms | 16 - 199 MB | NPU
81
+ | generator | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 38.125 ms | 16 - 20 MB | NPU
82
+ | generator | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 21.94 ms | 18 - 20 MB | NPU
83
+ | generator | ONNX | float | Qualcomm® QCS8450 | 35.502 ms | 16 - 199 MB | NPU
84
+ | generator | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 34.003 ms | 17 - 21 MB | NPU
85
+ | generator | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 22.403 ms | 89 - 89 MB | NPU
86
+ | generator | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 13.285 ms | 15 - 170 MB | NPU
87
+ | generator | TFLITE | float | Qualcomm® SA8775P | 545.416 ms | 19 - 37 MB | CPU
88
+ | generator | TFLITE | float | Qualcomm® SA8650P | 545.416 ms | 19 - 37 MB | CPU
89
+ | generator | TFLITE | float | Qualcomm® SA8255P | 545.416 ms | 19 - 37 MB | CPU
90
+ | generator | TFLITE | float | Qualcomm® SA7255P | 2876.088 ms | 21 - 37 MB | CPU
91
 
92
  ## License
93
  * The license for the original implementation of First-Order-Motion-Model can be found
release_assets.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
- "version": "0.62.2",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
6
  "onnx": {
7
  "tool_versions": {
8
- "qairt": "2.45.0.260326154327",
9
  "onnx_runtime": "1.27.1"
10
  },
11
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fomm/releases/v0.62.2/fomm-onnx-float.zip"
12
  }
13
  }
14
  }
 
1
  {
2
+ "version": "0.63.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
6
  "onnx": {
7
  "tool_versions": {
8
+ "qairt": "2.50.0.260828221209",
9
  "onnx_runtime": "1.27.1"
10
  },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fomm/releases/v0.63.0/fomm-onnx-float.zip"
12
  }
13
  }
14
  }