qaihm-bot commited on
Commit
62dfacb
·
verified ·
1 Parent(s): 4194132

See https://github.com/quic/ai-hub-models/releases/v0.33.0 for changelog.

This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +51 -51
  2. precompiled/qualcomm-qcs8275-proxy/Stable-Diffusion-v2.1_text_encoder_w8a16.bin +3 -0
  3. precompiled/qualcomm-qcs8275-proxy/Stable-Diffusion-v2.1_unet_w8a16.bin +3 -0
  4. precompiled/qualcomm-qcs8275-proxy/Stable-Diffusion-v2.1_vae_w8a16.bin +3 -0
  5. precompiled/qualcomm-qcs8275-proxy/sdk_versions.yml +3 -0
  6. precompiled/qualcomm-qcs8550-proxy/Stable-Diffusion-v2.1_text_encoder_w8a16.bin +3 -0
  7. precompiled/qualcomm-qcs8550-proxy/Stable-Diffusion-v2.1_unet_w8a16.bin +3 -0
  8. precompiled/qualcomm-qcs8550-proxy/Stable-Diffusion-v2.1_vae_w8a16.bin +3 -0
  9. precompiled/qualcomm-qcs8550-proxy/sdk_versions.yml +3 -0
  10. precompiled/qualcomm-qcs9075-proxy/Stable-Diffusion-v2.1_text_encoder_w8a16.bin +3 -0
  11. precompiled/qualcomm-qcs9075-proxy/Stable-Diffusion-v2.1_unet_w8a16.bin +3 -0
  12. precompiled/qualcomm-qcs9075-proxy/Stable-Diffusion-v2.1_vae_w8a16.bin +3 -0
  13. precompiled/qualcomm-qcs9075-proxy/sdk_versions.yml +3 -0
  14. precompiled/qualcomm-sa7255p/Stable-Diffusion-v2.1_text_encoder_w8a16.bin +3 -0
  15. precompiled/qualcomm-sa7255p/Stable-Diffusion-v2.1_unet_w8a16.bin +3 -0
  16. precompiled/qualcomm-sa7255p/Stable-Diffusion-v2.1_vae_w8a16.bin +3 -0
  17. precompiled/qualcomm-sa7255p/sdk_versions.yml +3 -0
  18. precompiled/qualcomm-sa8255p-proxy/Stable-Diffusion-v2.1_text_encoder_w8a16.bin +3 -0
  19. precompiled/qualcomm-sa8255p-proxy/Stable-Diffusion-v2.1_unet_w8a16.bin +3 -0
  20. precompiled/qualcomm-sa8255p-proxy/Stable-Diffusion-v2.1_vae_w8a16.bin +3 -0
  21. precompiled/qualcomm-sa8255p-proxy/sdk_versions.yml +3 -0
  22. precompiled/qualcomm-sa8650p-proxy/Stable-Diffusion-v2.1_text_encoder_w8a16.bin +3 -0
  23. precompiled/qualcomm-sa8650p-proxy/Stable-Diffusion-v2.1_unet_w8a16.bin +3 -0
  24. precompiled/qualcomm-sa8650p-proxy/Stable-Diffusion-v2.1_vae_w8a16.bin +3 -0
  25. precompiled/qualcomm-sa8650p-proxy/sdk_versions.yml +3 -0
  26. precompiled/qualcomm-sa8775p/Stable-Diffusion-v2.1_text_encoder_w8a16.bin +3 -0
  27. precompiled/qualcomm-sa8775p/Stable-Diffusion-v2.1_unet_w8a16.bin +3 -0
  28. precompiled/qualcomm-sa8775p/Stable-Diffusion-v2.1_vae_w8a16.bin +3 -0
  29. precompiled/qualcomm-sa8775p/sdk_versions.yml +3 -0
  30. precompiled/qualcomm-snapdragon-8-elite/Stable-Diffusion-v2.1_text_encoder_w8a16.bin +3 -0
  31. precompiled/qualcomm-snapdragon-8-elite/Stable-Diffusion-v2.1_text_encoder_w8a16.onnx.zip +3 -0
  32. precompiled/qualcomm-snapdragon-8-elite/Stable-Diffusion-v2.1_unet_w8a16.bin +3 -0
  33. precompiled/qualcomm-snapdragon-8-elite/Stable-Diffusion-v2.1_unet_w8a16.onnx.zip +3 -0
  34. precompiled/qualcomm-snapdragon-8-elite/Stable-Diffusion-v2.1_vae_w8a16.bin +3 -0
  35. precompiled/qualcomm-snapdragon-8-elite/Stable-Diffusion-v2.1_vae_w8a16.onnx.zip +3 -0
  36. precompiled/qualcomm-snapdragon-8-elite/sdk_versions.yml +5 -0
  37. precompiled/qualcomm-snapdragon-8gen2/Stable-Diffusion-v2.1_text_encoder_w8a16.bin +3 -0
  38. precompiled/qualcomm-snapdragon-8gen2/Stable-Diffusion-v2.1_text_encoder_w8a16.onnx.zip +3 -0
  39. precompiled/qualcomm-snapdragon-8gen2/Stable-Diffusion-v2.1_unet_w8a16.bin +3 -0
  40. precompiled/qualcomm-snapdragon-8gen2/Stable-Diffusion-v2.1_unet_w8a16.onnx.zip +3 -0
  41. precompiled/qualcomm-snapdragon-8gen2/Stable-Diffusion-v2.1_vae_w8a16.bin +3 -0
  42. precompiled/qualcomm-snapdragon-8gen2/Stable-Diffusion-v2.1_vae_w8a16.onnx.zip +3 -0
  43. precompiled/qualcomm-snapdragon-8gen2/sdk_versions.yml +5 -0
  44. precompiled/qualcomm-snapdragon-8gen3/Stable-Diffusion-v2.1_text_encoder_w8a16.bin +3 -0
  45. precompiled/qualcomm-snapdragon-8gen3/Stable-Diffusion-v2.1_text_encoder_w8a16.onnx.zip +3 -0
  46. precompiled/qualcomm-snapdragon-8gen3/Stable-Diffusion-v2.1_unet_w8a16.bin +3 -0
  47. precompiled/qualcomm-snapdragon-8gen3/Stable-Diffusion-v2.1_unet_w8a16.onnx.zip +3 -0
  48. precompiled/qualcomm-snapdragon-8gen3/Stable-Diffusion-v2.1_vae_w8a16.bin +3 -0
  49. precompiled/qualcomm-snapdragon-8gen3/Stable-Diffusion-v2.1_vae_w8a16.onnx.zip +3 -0
  50. precompiled/qualcomm-snapdragon-8gen3/sdk_versions.yml +5 -0
README.md CHANGED
@@ -32,51 +32,51 @@ More details on model performance across various devices, can be found
32
 
33
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
34
  |---|---|---|---|---|---|---|---|---|
35
- | text_encoder | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 18.572 ms | 0 - 9 MB | NPU | Use Export Script |
36
- | text_encoder | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 8.205 ms | 0 - 2 MB | NPU | Use Export Script |
37
- | text_encoder | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 8.392 ms | 0 - 9 MB | NPU | Use Export Script |
38
- | text_encoder | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 18.572 ms | 0 - 9 MB | NPU | Use Export Script |
39
- | text_encoder | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 8.224 ms | 0 - 2 MB | NPU | Use Export Script |
40
- | text_encoder | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 8.216 ms | 0 - 3 MB | NPU | Use Export Script |
41
- | text_encoder | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 8.392 ms | 0 - 9 MB | NPU | Use Export Script |
42
- | text_encoder | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_CONTEXT_BINARY | 8.233 ms | 0 - 2 MB | NPU | Use Export Script |
43
- | text_encoder | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | PRECOMPILED_QNN_ONNX | 8.21 ms | 0 - 386 MB | NPU | Use Export Script |
44
- | text_encoder | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 5.646 ms | 0 - 19 MB | NPU | Use Export Script |
45
- | text_encoder | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 5.466 ms | 0 - 19 MB | NPU | Use Export Script |
46
- | text_encoder | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_CONTEXT_BINARY | 5.133 ms | 0 - 14 MB | NPU | Use Export Script |
47
- | text_encoder | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | PRECOMPILED_QNN_ONNX | 5.372 ms | 0 - 18 MB | NPU | Use Export Script |
48
- | text_encoder | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 8.633 ms | 0 - 0 MB | NPU | Use Export Script |
49
- | text_encoder | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 8.256 ms | 379 - 379 MB | NPU | Use Export Script |
50
- | unet | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 232.535 ms | 0 - 8 MB | NPU | Use Export Script |
51
- | unet | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 93.804 ms | 0 - 2 MB | NPU | Use Export Script |
52
- | unet | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 87.82 ms | 0 - 8 MB | NPU | Use Export Script |
53
- | unet | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 232.535 ms | 0 - 8 MB | NPU | Use Export Script |
54
- | unet | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 94.034 ms | 0 - 3 MB | NPU | Use Export Script |
55
- | unet | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 94.829 ms | 0 - 3 MB | NPU | Use Export Script |
56
- | unet | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 87.82 ms | 0 - 8 MB | NPU | Use Export Script |
57
- | unet | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_CONTEXT_BINARY | 93.81 ms | 0 - 2 MB | NPU | Use Export Script |
58
- | unet | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | PRECOMPILED_QNN_ONNX | 95.775 ms | 0 - 898 MB | NPU | Use Export Script |
59
- | unet | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 66.1 ms | 0 - 18 MB | NPU | Use Export Script |
60
- | unet | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 66.978 ms | 0 - 17 MB | NPU | Use Export Script |
61
- | unet | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_CONTEXT_BINARY | 58.317 ms | 0 - 15 MB | NPU | Use Export Script |
62
- | unet | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | PRECOMPILED_QNN_ONNX | 58.189 ms | 0 - 15 MB | NPU | Use Export Script |
63
- | unet | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 95.257 ms | 0 - 0 MB | NPU | Use Export Script |
64
- | unet | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 96.242 ms | 842 - 842 MB | NPU | Use Export Script |
65
- | vae | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 718.615 ms | 0 - 9 MB | NPU | Use Export Script |
66
- | vae | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 270.88 ms | 0 - 3 MB | NPU | Use Export Script |
67
- | vae | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 249.022 ms | 0 - 10 MB | NPU | Use Export Script |
68
- | vae | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 718.615 ms | 0 - 9 MB | NPU | Use Export Script |
69
- | vae | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 276.47 ms | 0 - 3 MB | NPU | Use Export Script |
70
- | vae | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 273.324 ms | 0 - 2 MB | NPU | Use Export Script |
71
- | vae | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 249.022 ms | 0 - 10 MB | NPU | Use Export Script |
72
- | vae | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_CONTEXT_BINARY | 268.934 ms | 0 - 2 MB | NPU | Use Export Script |
73
- | vae | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | PRECOMPILED_QNN_ONNX | 271.01 ms | 0 - 68 MB | NPU | Use Export Script |
74
- | vae | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 202.979 ms | 0 - 20 MB | NPU | Use Export Script |
75
- | vae | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 203.271 ms | 3 - 21 MB | NPU | Use Export Script |
76
- | vae | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_CONTEXT_BINARY | 193.901 ms | 0 - 14 MB | NPU | Use Export Script |
77
- | vae | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | PRECOMPILED_QNN_ONNX | 194.085 ms | 3 - 17 MB | NPU | Use Export Script |
78
- | vae | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 265.475 ms | 0 - 0 MB | NPU | Use Export Script |
79
- | vae | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 264.466 ms | 63 - 63 MB | NPU | Use Export Script |
80
 
81
  ## Deploy to Snapdragon X Elite NPU
82
  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.
@@ -146,8 +146,8 @@ Profiling Results
146
  text_encoder
147
  Device : cs_8275 (ANDROID 14)
148
  Runtime : QNN_CONTEXT_BINARY
149
- Estimated inference time (ms) : 18.6
150
- Estimated peak memory usage (MB): [0, 9]
151
  Total # Ops : 788
152
  Compute Unit(s) : npu (788 ops) gpu (0 ops) cpu (0 ops)
153
 
@@ -155,7 +155,7 @@ Compute Unit(s) : npu (788 ops) gpu (0 ops) cpu (0 ops)
155
  unet
156
  Device : cs_8275 (ANDROID 14)
157
  Runtime : QNN_CONTEXT_BINARY
158
- Estimated inference time (ms) : 232.5
159
  Estimated peak memory usage (MB): [0, 8]
160
  Total # Ops : 5784
161
  Compute Unit(s) : npu (5784 ops) gpu (0 ops) cpu (0 ops)
@@ -164,10 +164,10 @@ Compute Unit(s) : npu (5784 ops) gpu (0 ops) cpu (0 ops)
164
  vae
165
  Device : cs_8275 (ANDROID 14)
166
  Runtime : QNN_CONTEXT_BINARY
167
- Estimated inference time (ms) : 718.6
168
  Estimated peak memory usage (MB): [0, 9]
169
- Total # Ops : 174
170
- Compute Unit(s) : npu (174 ops) gpu (0 ops) cpu (0 ops)
171
  ```
172
 
173
 
 
32
 
33
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
34
  |---|---|---|---|---|---|---|---|---|
35
+ | text_encoder | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 18.499 ms | 0 - 8 MB | NPU | Use Export Script |
36
+ | text_encoder | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 8.205 ms | 0 - 3 MB | NPU | Use Export Script |
37
+ | text_encoder | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 8.377 ms | 0 - 9 MB | NPU | Use Export Script |
38
+ | text_encoder | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 18.499 ms | 0 - 8 MB | NPU | Use Export Script |
39
+ | text_encoder | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 8.366 ms | 0 - 2 MB | NPU | Use Export Script |
40
+ | text_encoder | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 8.216 ms | 0 - 2 MB | NPU | Use Export Script |
41
+ | text_encoder | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 8.377 ms | 0 - 9 MB | NPU | Use Export Script |
42
+ | text_encoder | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_CONTEXT_BINARY | 8.285 ms | 0 - 7 MB | NPU | Use Export Script |
43
+ | text_encoder | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | PRECOMPILED_QNN_ONNX | 8.141 ms | 0 - 387 MB | NPU | Use Export Script |
44
+ | text_encoder | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 5.601 ms | 0 - 18 MB | NPU | Use Export Script |
45
+ | text_encoder | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 5.404 ms | 0 - 19 MB | NPU | Use Export Script |
46
+ | text_encoder | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_CONTEXT_BINARY | 4.56 ms | 0 - 15 MB | NPU | Use Export Script |
47
+ | text_encoder | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | PRECOMPILED_QNN_ONNX | 5.312 ms | 0 - 14 MB | NPU | Use Export Script |
48
+ | text_encoder | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 8.652 ms | 0 - 0 MB | NPU | Use Export Script |
49
+ | text_encoder | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 8.311 ms | 378 - 378 MB | NPU | Use Export Script |
50
+ | unet | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 232.583 ms | 0 - 8 MB | NPU | Use Export Script |
51
+ | unet | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 93.286 ms | 0 - 2 MB | NPU | Use Export Script |
52
+ | unet | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 87.78 ms | 0 - 9 MB | NPU | Use Export Script |
53
+ | unet | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 232.583 ms | 0 - 8 MB | NPU | Use Export Script |
54
+ | unet | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 93.785 ms | 0 - 3 MB | NPU | Use Export Script |
55
+ | unet | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 93.873 ms | 0 - 3 MB | NPU | Use Export Script |
56
+ | unet | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 87.78 ms | 0 - 9 MB | NPU | Use Export Script |
57
+ | unet | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_CONTEXT_BINARY | 93.717 ms | 0 - 7 MB | NPU | Use Export Script |
58
+ | unet | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | PRECOMPILED_QNN_ONNX | 95.033 ms | 0 - 898 MB | NPU | Use Export Script |
59
+ | unet | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 66.248 ms | 0 - 18 MB | NPU | Use Export Script |
60
+ | unet | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 67.516 ms | 0 - 14 MB | NPU | Use Export Script |
61
+ | unet | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_CONTEXT_BINARY | 58.258 ms | 0 - 14 MB | NPU | Use Export Script |
62
+ | unet | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | PRECOMPILED_QNN_ONNX | 58.617 ms | 0 - 19 MB | NPU | Use Export Script |
63
+ | unet | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 95.326 ms | 0 - 0 MB | NPU | Use Export Script |
64
+ | unet | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 96.279 ms | 843 - 843 MB | NPU | Use Export Script |
65
+ | vae | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 719.113 ms | 0 - 9 MB | NPU | Use Export Script |
66
+ | vae | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 270.059 ms | 1 - 3 MB | NPU | Use Export Script |
67
+ | vae | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 249.046 ms | 0 - 10 MB | NPU | Use Export Script |
68
+ | vae | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 719.113 ms | 0 - 9 MB | NPU | Use Export Script |
69
+ | vae | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 271.52 ms | 0 - 3 MB | NPU | Use Export Script |
70
+ | vae | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 271.625 ms | 0 - 4 MB | NPU | Use Export Script |
71
+ | vae | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 249.046 ms | 0 - 10 MB | NPU | Use Export Script |
72
+ | vae | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_CONTEXT_BINARY | 269.852 ms | 0 - 2 MB | NPU | Use Export Script |
73
+ | vae | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | PRECOMPILED_QNN_ONNX | 274.742 ms | 0 - 68 MB | NPU | Use Export Script |
74
+ | vae | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 202.714 ms | 0 - 21 MB | NPU | Use Export Script |
75
+ | vae | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 203.279 ms | 3 - 22 MB | NPU | Use Export Script |
76
+ | vae | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_CONTEXT_BINARY | 175.114 ms | 0 - 14 MB | NPU | Use Export Script |
77
+ | vae | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | PRECOMPILED_QNN_ONNX | 174.448 ms | 3 - 17 MB | NPU | Use Export Script |
78
+ | vae | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 265.137 ms | 0 - 0 MB | NPU | Use Export Script |
79
+ | vae | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 264.748 ms | 62 - 62 MB | NPU | Use Export Script |
80
 
81
  ## Deploy to Snapdragon X Elite NPU
82
  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.
 
146
  text_encoder
147
  Device : cs_8275 (ANDROID 14)
148
  Runtime : QNN_CONTEXT_BINARY
149
+ Estimated inference time (ms) : 18.5
150
+ Estimated peak memory usage (MB): [0, 8]
151
  Total # Ops : 788
152
  Compute Unit(s) : npu (788 ops) gpu (0 ops) cpu (0 ops)
153
 
 
155
  unet
156
  Device : cs_8275 (ANDROID 14)
157
  Runtime : QNN_CONTEXT_BINARY
158
+ Estimated inference time (ms) : 232.6
159
  Estimated peak memory usage (MB): [0, 8]
160
  Total # Ops : 5784
161
  Compute Unit(s) : npu (5784 ops) gpu (0 ops) cpu (0 ops)
 
164
  vae
165
  Device : cs_8275 (ANDROID 14)
166
  Runtime : QNN_CONTEXT_BINARY
167
+ Estimated inference time (ms) : 719.1
168
  Estimated peak memory usage (MB): [0, 9]
169
+ Total # Ops : 175
170
+ Compute Unit(s) : npu (175 ops) gpu (0 ops) cpu (0 ops)
171
  ```
172
 
173
 
precompiled/qualcomm-qcs8275-proxy/Stable-Diffusion-v2.1_text_encoder_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0893b248a5ed07e9e512d5f98924609d887cbcd58ff32628bce52488418353a
3
+ size 395968368
precompiled/qualcomm-qcs8275-proxy/Stable-Diffusion-v2.1_unet_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:282c4fddc3e8b7bbd0f3c4a0180135971da4e3e7d9a65df9106a777dc885e68d
3
+ size 881541672
precompiled/qualcomm-qcs8275-proxy/Stable-Diffusion-v2.1_vae_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd2393803370617bdadedfb98d21eb1d056f5628b5e0f1185060417b696781e4
3
+ size 64561368
precompiled/qualcomm-qcs8275-proxy/sdk_versions.yml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
precompiled/qualcomm-qcs8550-proxy/Stable-Diffusion-v2.1_text_encoder_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58dba2daf7e4c9430f68e335b4258002ab34df6c427784d095fbffa0137a7773
3
+ size 395964264
precompiled/qualcomm-qcs8550-proxy/Stable-Diffusion-v2.1_unet_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4aa32f750e6833e7d0f06432a9fb692b098996a1f41b2fd117532cbee365b9f
3
+ size 881553888
precompiled/qualcomm-qcs8550-proxy/Stable-Diffusion-v2.1_vae_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d29501a59fa17cdabeb22bae4c90a0f7e55f1c6579b1f1731a01db852379d5b
3
+ size 64569488
precompiled/qualcomm-qcs8550-proxy/sdk_versions.yml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
precompiled/qualcomm-qcs9075-proxy/Stable-Diffusion-v2.1_text_encoder_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0862c7fae278ffb85bf82bd13f6623a67e8a752a6c8b6cf0435a53c2ec034e4a
3
+ size 395972464
precompiled/qualcomm-qcs9075-proxy/Stable-Diffusion-v2.1_unet_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e7940aca3c2ee50f4cc04e5ac6d7a10b7faf9ed5abfa61770f9ab92a4a859a5
3
+ size 881541608
precompiled/qualcomm-qcs9075-proxy/Stable-Diffusion-v2.1_vae_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bc27fb430536b48bcdbfca58891c264e57ba000a1cf57d0e443fa2046c7d11f
3
+ size 64569496
precompiled/qualcomm-qcs9075-proxy/sdk_versions.yml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
precompiled/qualcomm-sa7255p/Stable-Diffusion-v2.1_text_encoder_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0893b248a5ed07e9e512d5f98924609d887cbcd58ff32628bce52488418353a
3
+ size 395968368
precompiled/qualcomm-sa7255p/Stable-Diffusion-v2.1_unet_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:282c4fddc3e8b7bbd0f3c4a0180135971da4e3e7d9a65df9106a777dc885e68d
3
+ size 881541672
precompiled/qualcomm-sa7255p/Stable-Diffusion-v2.1_vae_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd2393803370617bdadedfb98d21eb1d056f5628b5e0f1185060417b696781e4
3
+ size 64561368
precompiled/qualcomm-sa7255p/sdk_versions.yml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
precompiled/qualcomm-sa8255p-proxy/Stable-Diffusion-v2.1_text_encoder_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58dba2daf7e4c9430f68e335b4258002ab34df6c427784d095fbffa0137a7773
3
+ size 395964264
precompiled/qualcomm-sa8255p-proxy/Stable-Diffusion-v2.1_unet_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4aa32f750e6833e7d0f06432a9fb692b098996a1f41b2fd117532cbee365b9f
3
+ size 881553888
precompiled/qualcomm-sa8255p-proxy/Stable-Diffusion-v2.1_vae_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d29501a59fa17cdabeb22bae4c90a0f7e55f1c6579b1f1731a01db852379d5b
3
+ size 64569488
precompiled/qualcomm-sa8255p-proxy/sdk_versions.yml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
precompiled/qualcomm-sa8650p-proxy/Stable-Diffusion-v2.1_text_encoder_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58dba2daf7e4c9430f68e335b4258002ab34df6c427784d095fbffa0137a7773
3
+ size 395964264
precompiled/qualcomm-sa8650p-proxy/Stable-Diffusion-v2.1_unet_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4aa32f750e6833e7d0f06432a9fb692b098996a1f41b2fd117532cbee365b9f
3
+ size 881553888
precompiled/qualcomm-sa8650p-proxy/Stable-Diffusion-v2.1_vae_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d29501a59fa17cdabeb22bae4c90a0f7e55f1c6579b1f1731a01db852379d5b
3
+ size 64569488
precompiled/qualcomm-sa8650p-proxy/sdk_versions.yml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
precompiled/qualcomm-sa8775p/Stable-Diffusion-v2.1_text_encoder_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0862c7fae278ffb85bf82bd13f6623a67e8a752a6c8b6cf0435a53c2ec034e4a
3
+ size 395972464
precompiled/qualcomm-sa8775p/Stable-Diffusion-v2.1_unet_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e7940aca3c2ee50f4cc04e5ac6d7a10b7faf9ed5abfa61770f9ab92a4a859a5
3
+ size 881541608
precompiled/qualcomm-sa8775p/Stable-Diffusion-v2.1_vae_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bc27fb430536b48bcdbfca58891c264e57ba000a1cf57d0e443fa2046c7d11f
3
+ size 64569496
precompiled/qualcomm-sa8775p/sdk_versions.yml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
precompiled/qualcomm-snapdragon-8-elite/Stable-Diffusion-v2.1_text_encoder_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b77c0806f3894b0b619b58588ba2aef6d04e6e6de3649e4daf5c9e455bb79b40
3
+ size 395919208
precompiled/qualcomm-snapdragon-8-elite/Stable-Diffusion-v2.1_text_encoder_w8a16.onnx.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca90a0a2acc809fb615bec951a42af64acbc381eb82ca7a6b11e82483758ffe3
3
+ size 299319869
precompiled/qualcomm-snapdragon-8-elite/Stable-Diffusion-v2.1_unet_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56d95abffa3014feac19241e0f29a95506a2fc6886c247a440a432ea1873a0a6
3
+ size 881054176
precompiled/qualcomm-snapdragon-8-elite/Stable-Diffusion-v2.1_unet_w8a16.onnx.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:257ae5941163b9572e3874901ea725f18beb8c1b8565b15da51ccdcfb12cfe81
3
+ size 543437950
precompiled/qualcomm-snapdragon-8-elite/Stable-Diffusion-v2.1_vae_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7597181185acee04dd556e6802139b936e01e32be002a6ab4c691bcf77df8020
3
+ size 64508048
precompiled/qualcomm-snapdragon-8-elite/Stable-Diffusion-v2.1_vae_w8a16.onnx.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed657a5eb75e6781e87db65e9a4bde233d78809050d61b7fb1e270dff3470a59
3
+ size 40814630
precompiled/qualcomm-snapdragon-8-elite/sdk_versions.yml ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
4
+ precompiled_qnn_onnx:
5
+ qairt: 2.33.2.250410134701_117956
precompiled/qualcomm-snapdragon-8gen2/Stable-Diffusion-v2.1_text_encoder_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58dba2daf7e4c9430f68e335b4258002ab34df6c427784d095fbffa0137a7773
3
+ size 395964264
precompiled/qualcomm-snapdragon-8gen2/Stable-Diffusion-v2.1_text_encoder_w8a16.onnx.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d685e824e643fb518d389a7de2b15a3bdb85979d4b1a0bb75b81c15740aa5d7b
3
+ size 299331596
precompiled/qualcomm-snapdragon-8gen2/Stable-Diffusion-v2.1_unet_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4aa32f750e6833e7d0f06432a9fb692b098996a1f41b2fd117532cbee365b9f
3
+ size 881553888
precompiled/qualcomm-snapdragon-8gen2/Stable-Diffusion-v2.1_unet_w8a16.onnx.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:258104e61a0dd1e3444bc342355d2da94dab2a8191134d4598029d1ccb746b0d
3
+ size 543680160
precompiled/qualcomm-snapdragon-8gen2/Stable-Diffusion-v2.1_vae_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d29501a59fa17cdabeb22bae4c90a0f7e55f1c6579b1f1731a01db852379d5b
3
+ size 64569488
precompiled/qualcomm-snapdragon-8gen2/Stable-Diffusion-v2.1_vae_w8a16.onnx.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7154c498319e4795bbb229f063d81620f9e45bc625748cd0252c316d2605d7cc
3
+ size 40964108
precompiled/qualcomm-snapdragon-8gen2/sdk_versions.yml ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
4
+ precompiled_qnn_onnx:
5
+ qairt: 2.33.2.250410134701_117956
precompiled/qualcomm-snapdragon-8gen3/Stable-Diffusion-v2.1_text_encoder_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:527eb4a42cf5c5499739e6893ae3bee99f680f0cba622e474520b1382a054117
3
+ size 395956072
precompiled/qualcomm-snapdragon-8gen3/Stable-Diffusion-v2.1_text_encoder_w8a16.onnx.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d29aa97562086641d0e3c2cd6f009563d9931b29b75286b68ae6a9ccd106701e
3
+ size 299344556
precompiled/qualcomm-snapdragon-8gen3/Stable-Diffusion-v2.1_unet_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6ceb97b6aea50235ae3fb78a184b145f4b81d18df7137b9de8f2c64a3702b4d
3
+ size 881521120
precompiled/qualcomm-snapdragon-8gen3/Stable-Diffusion-v2.1_unet_w8a16.onnx.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f09cc80e7acbbace8d2349f06b871803f2f9f94c091036a6c11dbe6f11da743
3
+ size 543646179
precompiled/qualcomm-snapdragon-8gen3/Stable-Diffusion-v2.1_vae_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bf3f201f0e193163ebae0ce728d157a209b54e7c4109cb04f95c3284a04be97
3
+ size 64569488
precompiled/qualcomm-snapdragon-8gen3/Stable-Diffusion-v2.1_vae_w8a16.onnx.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac05bddf6179fd97d5ccd6fc2ac526f81a701ae05e172185be23f6d96051143f
3
+ size 40973078
precompiled/qualcomm-snapdragon-8gen3/sdk_versions.yml ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
4
+ precompiled_qnn_onnx:
5
+ qairt: 2.33.2.250410134701_117956