v0.30.5
Browse filesSee https://github.com/quic/ai-hub-models/releases/v0.30.5 for changelog.
README.md
CHANGED
|
@@ -36,52 +36,58 @@ More details on model performance across various devices, can be found
|
|
| 36 |
|
| 37 |
| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
|
| 38 |
|---|---|---|---|---|---|---|---|---|
|
| 39 |
-
|
|
| 40 |
-
|
|
| 41 |
-
|
|
| 42 |
-
|
|
| 43 |
-
|
|
| 44 |
-
|
|
| 45 |
-
|
|
| 46 |
-
|
|
| 47 |
-
|
|
| 48 |
-
|
|
| 49 |
-
|
|
| 50 |
-
|
|
| 51 |
-
|
|
| 52 |
-
|
|
| 53 |
-
|
|
| 54 |
-
|
|
| 55 |
-
|
|
| 56 |
-
|
|
| 57 |
-
|
|
| 58 |
-
|
|
| 59 |
-
|
|
| 60 |
-
|
|
| 61 |
-
|
|
| 62 |
-
|
|
| 63 |
-
|
|
| 64 |
-
|
|
| 65 |
-
|
|
| 66 |
-
|
|
| 67 |
-
|
|
| 68 |
-
|
|
| 69 |
-
|
|
| 70 |
-
|
|
| 71 |
-
|
|
| 72 |
-
|
|
| 73 |
-
|
|
| 74 |
-
|
|
| 75 |
-
|
|
| 76 |
-
|
|
| 77 |
-
|
|
| 78 |
-
|
|
| 79 |
-
|
|
| 80 |
-
|
|
| 81 |
-
|
|
| 82 |
-
|
|
| 83 |
-
|
|
| 84 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 85 |
|
| 86 |
|
| 87 |
|
|
@@ -141,31 +147,31 @@ python -m qai_hub_models.models.stable_diffusion_v2_1.export
|
|
| 141 |
```
|
| 142 |
Profiling Results
|
| 143 |
------------------------------------------------------------
|
| 144 |
-
|
| 145 |
Device : cs_8275 (ANDROID 14)
|
| 146 |
Runtime : QNN
|
| 147 |
-
Estimated inference time (ms) :
|
| 148 |
Estimated peak memory usage (MB): [0, 9]
|
| 149 |
-
Total # Ops :
|
| 150 |
-
Compute Unit(s) : npu (
|
| 151 |
|
| 152 |
------------------------------------------------------------
|
| 153 |
-
|
| 154 |
Device : cs_8275 (ANDROID 14)
|
| 155 |
Runtime : QNN
|
| 156 |
-
Estimated inference time (ms) :
|
| 157 |
-
Estimated peak memory usage (MB): [
|
| 158 |
Total # Ops : 5783
|
| 159 |
Compute Unit(s) : npu (5783 ops) gpu (0 ops) cpu (0 ops)
|
| 160 |
|
| 161 |
------------------------------------------------------------
|
| 162 |
-
|
| 163 |
Device : cs_8275 (ANDROID 14)
|
| 164 |
Runtime : QNN
|
| 165 |
-
Estimated inference time (ms) :
|
| 166 |
Estimated peak memory usage (MB): [0, 9]
|
| 167 |
-
Total # Ops :
|
| 168 |
-
Compute Unit(s) : npu (
|
| 169 |
```
|
| 170 |
|
| 171 |
|
|
|
|
| 36 |
|
| 37 |
| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
|
| 38 |
|---|---|---|---|---|---|---|---|---|
|
| 39 |
+
| text_encoder | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 18.456 ms | 0 - 9 MB | NPU | Use Export Script |
|
| 40 |
+
| text_encoder | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 8.173 ms | 0 - 2 MB | NPU | Use Export Script |
|
| 41 |
+
| text_encoder | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 8.367 ms | 0 - 9 MB | NPU | Use Export Script |
|
| 42 |
+
| text_encoder | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN | 18.456 ms | 0 - 9 MB | NPU | Use Export Script |
|
| 43 |
+
| text_encoder | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 8.393 ms | 0 - 2 MB | NPU | Use Export Script |
|
| 44 |
+
| text_encoder | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 8.257 ms | 0 - 2 MB | NPU | Use Export Script |
|
| 45 |
+
| text_encoder | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN | 8.367 ms | 0 - 9 MB | NPU | Use Export Script |
|
| 46 |
+
| text_encoder | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 8.245 ms | 0 - 2 MB | NPU | Use Export Script |
|
| 47 |
+
| text_encoder | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 8.133 ms | 0 - 386 MB | NPU | [Stable-Diffusion-v2.1.onnx](https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/blob/main/Stable-Diffusion-v2.1_w8a16.onnx) |
|
| 48 |
+
| text_encoder | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 5.767 ms | 0 - 18 MB | NPU | Use Export Script |
|
| 49 |
+
| text_encoder | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 5.364 ms | 0 - 20 MB | NPU | [Stable-Diffusion-v2.1.onnx](https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/blob/main/Stable-Diffusion-v2.1_w8a16.onnx) |
|
| 50 |
+
| text_encoder | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 5.13 ms | 0 - 14 MB | NPU | Use Export Script |
|
| 51 |
+
| text_encoder | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 5.361 ms | 0 - 14 MB | NPU | [Stable-Diffusion-v2.1.onnx](https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/blob/main/Stable-Diffusion-v2.1_w8a16.onnx) |
|
| 52 |
+
| text_encoder | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 8.624 ms | 0 - 0 MB | NPU | Use Export Script |
|
| 53 |
+
| text_encoder | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 8.244 ms | 378 - 378 MB | NPU | [Stable-Diffusion-v2.1.onnx](https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/blob/main/Stable-Diffusion-v2.1_w8a16.onnx) |
|
| 54 |
+
| unet | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 232.337 ms | 2 - 9 MB | NPU | Use Export Script |
|
| 55 |
+
| unet | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 93.471 ms | 0 - 2 MB | NPU | Use Export Script |
|
| 56 |
+
| unet | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 87.875 ms | 0 - 8 MB | NPU | Use Export Script |
|
| 57 |
+
| unet | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN | 232.337 ms | 2 - 9 MB | NPU | Use Export Script |
|
| 58 |
+
| unet | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 93.998 ms | 0 - 3 MB | NPU | Use Export Script |
|
| 59 |
+
| unet | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 94.023 ms | 0 - 2 MB | NPU | Use Export Script |
|
| 60 |
+
| unet | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN | 87.875 ms | 0 - 8 MB | NPU | Use Export Script |
|
| 61 |
+
| unet | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 93.779 ms | 0 - 3 MB | NPU | Use Export Script |
|
| 62 |
+
| unet | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 94.913 ms | 0 - 898 MB | NPU | [Stable-Diffusion-v2.1.onnx](https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/blob/main/Stable-Diffusion-v2.1_w8a16.onnx) |
|
| 63 |
+
| unet | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 65.976 ms | 0 - 18 MB | NPU | Use Export Script |
|
| 64 |
+
| unet | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 68.382 ms | 0 - 16 MB | NPU | [Stable-Diffusion-v2.1.onnx](https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/blob/main/Stable-Diffusion-v2.1_w8a16.onnx) |
|
| 65 |
+
| unet | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 52.475 ms | 0 - 15 MB | NPU | Use Export Script |
|
| 66 |
+
| unet | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 58.492 ms | 0 - 18 MB | NPU | [Stable-Diffusion-v2.1.onnx](https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/blob/main/Stable-Diffusion-v2.1_w8a16.onnx) |
|
| 67 |
+
| unet | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 95.267 ms | 0 - 0 MB | NPU | Use Export Script |
|
| 68 |
+
| unet | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 96.199 ms | 842 - 842 MB | NPU | [Stable-Diffusion-v2.1.onnx](https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/blob/main/Stable-Diffusion-v2.1_w8a16.onnx) |
|
| 69 |
+
| vae | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 719.096 ms | 0 - 9 MB | NPU | Use Export Script |
|
| 70 |
+
| vae | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 267.027 ms | 0 - 3 MB | NPU | Use Export Script |
|
| 71 |
+
| vae | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 248.931 ms | 0 - 10 MB | NPU | Use Export Script |
|
| 72 |
+
| vae | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN | 719.096 ms | 0 - 9 MB | NPU | Use Export Script |
|
| 73 |
+
| vae | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 268.927 ms | 0 - 2 MB | NPU | Use Export Script |
|
| 74 |
+
| vae | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 267.889 ms | 0 - 2 MB | NPU | Use Export Script |
|
| 75 |
+
| vae | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN | 248.931 ms | 0 - 10 MB | NPU | Use Export Script |
|
| 76 |
+
| vae | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 269.837 ms | 0 - 2 MB | NPU | Use Export Script |
|
| 77 |
+
| vae | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 272.79 ms | 0 - 68 MB | NPU | [Stable-Diffusion-v2.1.onnx](https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/blob/main/Stable-Diffusion-v2.1_w8a16.onnx) |
|
| 78 |
+
| vae | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 202.859 ms | 0 - 21 MB | NPU | Use Export Script |
|
| 79 |
+
| vae | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 208.42 ms | 4 - 22 MB | NPU | [Stable-Diffusion-v2.1.onnx](https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/blob/main/Stable-Diffusion-v2.1_w8a16.onnx) |
|
| 80 |
+
| vae | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 175.718 ms | 0 - 15 MB | NPU | Use Export Script |
|
| 81 |
+
| vae | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 194.087 ms | 3 - 17 MB | NPU | [Stable-Diffusion-v2.1.onnx](https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/blob/main/Stable-Diffusion-v2.1_w8a16.onnx) |
|
| 82 |
+
| vae | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 265.086 ms | 0 - 0 MB | NPU | Use Export Script |
|
| 83 |
+
| vae | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 264.341 ms | 63 - 63 MB | NPU | [Stable-Diffusion-v2.1.onnx](https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/blob/main/Stable-Diffusion-v2.1_w8a16.onnx) |
|
| 84 |
+
|
| 85 |
+
## Deploy to Snapdragon X Elite NPU
|
| 86 |
+
Please follow the [Stable Diffusion Windows App](https://github.com/quic/ai-hub-apps/tree/main/apps/windows/python/StableDiffusion) tutorial to quantize model with custom weights.
|
| 87 |
+
|
| 88 |
+
## Quantize and Deploy Your Own Fine-Tuned Stable Diffusion
|
| 89 |
+
|
| 90 |
+
Please follow the [Quantize Stable Diffusion]({REPOSITORY_URL}/tutorials/stable_diffusion/quantize_stable_diffusion.md) tutorial to quantize model with custom weights.
|
| 91 |
|
| 92 |
|
| 93 |
|
|
|
|
| 147 |
```
|
| 148 |
Profiling Results
|
| 149 |
------------------------------------------------------------
|
| 150 |
+
text_encoder
|
| 151 |
Device : cs_8275 (ANDROID 14)
|
| 152 |
Runtime : QNN
|
| 153 |
+
Estimated inference time (ms) : 18.5
|
| 154 |
Estimated peak memory usage (MB): [0, 9]
|
| 155 |
+
Total # Ops : 787
|
| 156 |
+
Compute Unit(s) : npu (787 ops) gpu (0 ops) cpu (0 ops)
|
| 157 |
|
| 158 |
------------------------------------------------------------
|
| 159 |
+
unet
|
| 160 |
Device : cs_8275 (ANDROID 14)
|
| 161 |
Runtime : QNN
|
| 162 |
+
Estimated inference time (ms) : 232.3
|
| 163 |
+
Estimated peak memory usage (MB): [2, 9]
|
| 164 |
Total # Ops : 5783
|
| 165 |
Compute Unit(s) : npu (5783 ops) gpu (0 ops) cpu (0 ops)
|
| 166 |
|
| 167 |
------------------------------------------------------------
|
| 168 |
+
vae
|
| 169 |
Device : cs_8275 (ANDROID 14)
|
| 170 |
Runtime : QNN
|
| 171 |
+
Estimated inference time (ms) : 719.1
|
| 172 |
Estimated peak memory usage (MB): [0, 9]
|
| 173 |
+
Total # Ops : 173
|
| 174 |
+
Compute Unit(s) : npu (173 ops) gpu (0 ops) cpu (0 ops)
|
| 175 |
```
|
| 176 |
|
| 177 |
|