Hugging Face's logo

qualcomm
/
First-Order-Motion-Model

Image-to-Video
PyTorch
LiteRT
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
5428a47
·
verified ·
1 Parent(s): 56094e7

v0.38.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.38.0 for changelog.

Files changed (6) hide show
  1. First-Order-Motion-Model_FOMMDetector_float.onnx.zip +2 -2
  2. First-Order-Motion-Model_FOMMDetector_float.tflite +3 -0
  3. First-Order-Motion-Model_FOMMGenerator_float.onnx.zip +2 -2
  4. First-Order-Motion-Model_FOMMGenerator_float.tflite +3 -0
  5. README.md +11 -9
  6. tool-versions.yaml +3 -3
First-Order-Motion-Model_FOMMDetector_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1ac0a53b0faf9f55c1b49adf0e7c00117cf2d504609d11140d555a59cfd1f11
3
- size 52977711
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55942756f8018096362179ef634f3c13aed4f8d499db90e3b17c4526a1255926
3
+ size 52977812
First-Order-Motion-Model_FOMMDetector_float.tflite ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beaeb7cccd337a7f192883b2b98a1d4139310d93e171c211644bf65a857119b6
3
+ size 56880544
First-Order-Motion-Model_FOMMGenerator_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98c136adf74dca8437973b9a50d52a1e5f8fd794499877d2e51b66ce0aa6a559
3
- size 169943286
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:703cb87c211cd8c24f2bad7963b6d8fa05410774a4b89f24f35b8f56e4d7e1f8
3
+ size 169943525
First-Order-Motion-Model_FOMMGenerator_float.tflite ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dbfa2b1b5675059dc3c61a9f079fa03b92e6b8ed4454ad40fc5c15e87956f8d
3
+ size 182855312
README.md CHANGED
@@ -35,14 +35,16 @@ More details on model performance across various devices, can be found
35
 
36
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
- | FOMMDetector | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 4.527 ms | 0 - 91 MB | NPU | [First-Order-Motion-Model.onnx.zip](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx.zip) |
39
- | FOMMDetector | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 4.55 ms | 1 - 80 MB | NPU | [First-Order-Motion-Model.onnx.zip](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx.zip) |
40
- | FOMMDetector | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 3.392 ms | 0 - 23 MB | NPU | [First-Order-Motion-Model.onnx.zip](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx.zip) |
41
- | FOMMDetector | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 3.036 ms | 0 - 18 MB | NPU | [First-Order-Motion-Model.onnx.zip](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx.zip) |
42
- | FOMMGenerator | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 26.623 ms | 23 - 31 MB | NPU | [First-Order-Motion-Model.onnx.zip](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx.zip) |
43
- | FOMMGenerator | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 26.52 ms | 0 - 198 MB | NPU | [First-Order-Motion-Model.onnx.zip](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx.zip) |
44
- | FOMMGenerator | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 19.121 ms | 23 - 80 MB | NPU | [First-Order-Motion-Model.onnx.zip](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx.zip) |
45
- | FOMMGenerator | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 19.071 ms | 0 - 56 MB | NPU | [First-Order-Motion-Model.onnx.zip](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx.zip) |
 
 
46
 
47
 
48
 
@@ -124,7 +126,7 @@ from qai_hub_models.models.fomm import Model
124
  torch_model = Model.from_pretrained()
125
 
126
  # Device
127
- device = hub.Device("Samsung Galaxy S24")
128
 
129
  # Trace model
130
  input_shape = torch_model.get_input_spec()
 
35
 
36
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | FOMMDetector | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 4.613 ms | 0 - 102 MB | NPU | [First-Order-Motion-Model.onnx.zip](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx.zip) |
39
+ | FOMMDetector | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 3.431 ms | 0 - 21 MB | NPU | [First-Order-Motion-Model.onnx.zip](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx.zip) |
40
+ | FOMMDetector | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 3.037 ms | 0 - 24 MB | NPU | [First-Order-Motion-Model.tflite](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.tflite) |
41
+ | FOMMDetector | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 3.029 ms | 0 - 22 MB | NPU | [First-Order-Motion-Model.onnx.zip](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx.zip) |
42
+ | FOMMDetector | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 4.701 ms | 27 - 27 MB | NPU | [First-Order-Motion-Model.onnx.zip](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx.zip) |
43
+ | FOMMGenerator | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 24.278 ms | 0 - 103 MB | NPU | [First-Order-Motion-Model.onnx.zip](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx.zip) |
44
+ | FOMMGenerator | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 17.752 ms | 14 - 68 MB | NPU | [First-Order-Motion-Model.onnx.zip](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx.zip) |
45
+ | FOMMGenerator | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 32.077 ms | 1 - 729 MB | NPU | [First-Order-Motion-Model.tflite](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.tflite) |
46
+ | FOMMGenerator | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 15.797 ms | 19 - 70 MB | NPU | [First-Order-Motion-Model.onnx.zip](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx.zip) |
47
+ | FOMMGenerator | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 23.772 ms | 89 - 89 MB | NPU | [First-Order-Motion-Model.onnx.zip](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx.zip) |
48
 
49
 
50
 
 
126
  torch_model = Model.from_pretrained()
127
 
128
  # Device
129
+ device = hub.Device("Samsung Galaxy S25")
130
 
131
  # Trace model
132
  input_shape = torch_model.get_input_spec()
tool-versions.yaml CHANGED
@@ -1,4 +1,4 @@
1
  tool_versions:
2
- onnx:
3
- qairt: 2.36.4.250725200057_123280
4
- onnx_runtime: 1.22.0
 
1
  tool_versions:
2
+ tflite:
3
+ qairt: 2.38.0.250901140452_125126
4
+ tflite: 2.17.0