Hugging Face's logo

qualcomm
/
ControlNet

Unconditional Image Generation
PyTorch
generative_ai
android
Model card Files
xet
Community
1
qaihm-bot commited on
Commit
7f29e2b
·
verified ·
1 Parent(s): 8827de1

v0.30.2

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.30.2 for changelog.

Files changed (8) hide show
  1. ControlNet_Quantized.bin +0 -3
  2. README.md +39 -40
  3. TextEncoder_Quantized.bin +0 -3
  4. TextEncoder_Quantized.so +0 -3
  5. UNet_Quantized.bin +0 -3
  6. UNet_Quantized.so +0 -3
  7. VAEDecoder_Quantized.bin +0 -3
  8. VAEDecoder_Quantized.so +0 -3
ControlNet_Quantized.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9757acb27d03ef59e7ed5b658d59f0a668b6eb896f6d280e3c9116953945da5
3
- size 368625928
 
 
 
 
README.md CHANGED
@@ -1,9 +1,8 @@
1
  ---
2
  library_name: pytorch
3
- license: apache-2.0
4
  tags:
5
  - generative_ai
6
- - quantized
7
  - android
8
  pipeline_tag: unconditional-image-generation
9
 
@@ -27,7 +26,7 @@ More details on model performance across various devices, can be found
27
 
28
  ### Model Details
29
 
30
- - **Model Type:** Image generation
31
  - **Model Stats:**
32
  - Input: Text prompt and input image as a reference
33
  - Conditioning Input: Canny-Edge
@@ -37,20 +36,20 @@ More details on model performance across various devices, can be found
37
  - ControlNet Number of parameters: 361M
38
  - Model size: 1.4GB
39
 
40
- | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
41
  |---|---|---|---|---|---|---|---|---|
42
- | TextEncoder_Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 11.394 ms | 0 - 74 MB | UINT16 | NPU | [ControlNet.bin](https://huggingface.co/qualcomm/ControlNet/blob/main/TextEncoder_Quantized.bin) |
43
- | TextEncoder_Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 8.08 ms | 0 - 137 MB | UINT16 | NPU | [ControlNet.bin](https://huggingface.co/qualcomm/ControlNet/blob/main/TextEncoder_Quantized.bin) |
44
- | TextEncoder_Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 10.982 ms | 0 - 1 MB | UINT16 | NPU | Use Export Script |
45
- | UNet_Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 262.52 ms | 11 - 17 MB | UINT16 | NPU | [ControlNet.bin](https://huggingface.co/qualcomm/ControlNet/blob/main/UNet_Quantized.bin) |
46
- | UNet_Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 192.789 ms | 3 - 1247 MB | UINT16 | NPU | [ControlNet.bin](https://huggingface.co/qualcomm/ControlNet/blob/main/UNet_Quantized.bin) |
47
- | UNet_Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 260.158 ms | 14 - 15 MB | UINT16 | NPU | Use Export Script |
48
- | VAEDecoder_Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 390.243 ms | 0 - 36 MB | UINT16 | NPU | [ControlNet.bin](https://huggingface.co/qualcomm/ControlNet/blob/main/VAEDecoder_Quantized.bin) |
49
- | VAEDecoder_Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 294.404 ms | 0 - 88 MB | UINT16 | NPU | [ControlNet.bin](https://huggingface.co/qualcomm/ControlNet/blob/main/VAEDecoder_Quantized.bin) |
50
- | VAEDecoder_Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 379.548 ms | 0 - 1 MB | UINT16 | NPU | Use Export Script |
51
- | ControlNet_Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 100.33 ms | 2 - 68 MB | UINT16 | NPU | [ControlNet.bin](https://huggingface.co/qualcomm/ControlNet/blob/main/ControlNet_Quantized.bin) |
52
- | ControlNet_Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 76.94 ms | 0 - 533 MB | UINT16 | NPU | [ControlNet.bin](https://huggingface.co/qualcomm/ControlNet/blob/main/ControlNet_Quantized.bin) |
53
- | ControlNet_Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 103.52 ms | 2 - 3 MB | UINT16 | NPU | Use Export Script |
54
 
55
 
56
 
@@ -112,39 +111,39 @@ python -m qai_hub_models.models.controlnet.export
112
  Profiling Results
113
  ------------------------------------------------------------
114
  TextEncoder_Quantized
115
- Device : Samsung Galaxy S23 (13)
116
- Runtime : QNN
117
- Estimated inference time (ms) : 11.4
118
- Estimated peak memory usage (MB): [0, 74]
119
- Total # Ops : 570
120
- Compute Unit(s) : NPU (570 ops)
121
 
122
  ------------------------------------------------------------
123
  UNet_Quantized
124
- Device : Samsung Galaxy S23 (13)
125
- Runtime : QNN
126
- Estimated inference time (ms) : 262.5
127
- Estimated peak memory usage (MB): [11, 17]
128
- Total # Ops : 5434
129
- Compute Unit(s) : NPU (5434 ops)
130
 
131
  ------------------------------------------------------------
132
  VAEDecoder_Quantized
133
- Device : Samsung Galaxy S23 (13)
134
- Runtime : QNN
135
- Estimated inference time (ms) : 390.2
136
- Estimated peak memory usage (MB): [0, 36]
137
- Total # Ops : 409
138
- Compute Unit(s) : NPU (409 ops)
139
 
140
  ------------------------------------------------------------
141
  ControlNet_Quantized
142
- Device : Samsung Galaxy S23 (13)
143
- Runtime : QNN
144
- Estimated inference time (ms) : 100.3
145
- Estimated peak memory usage (MB): [2, 68]
146
- Total # Ops : 2406
147
- Compute Unit(s) : NPU (2406 ops)
148
  ```
149
 
150
 
 
1
  ---
2
  library_name: pytorch
3
+ license: other
4
  tags:
5
  - generative_ai
 
6
  - android
7
  pipeline_tag: unconditional-image-generation
8
 
 
26
 
27
  ### Model Details
28
 
29
+ - **Model Type:** Model_use_case.image_generation
30
  - **Model Stats:**
31
  - Input: Text prompt and input image as a reference
32
  - Conditioning Input: Canny-Edge
 
36
  - ControlNet Number of parameters: 361M
37
  - Model size: 1.4GB
38
 
39
+ | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
40
  |---|---|---|---|---|---|---|---|---|
41
+ | TextEncoder_Quantized | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 10.874 ms | 0 - 3 MB | NPU | Use Export Script |
42
+ | TextEncoder_Quantized | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 7.918 ms | 0 - 18 MB | NPU | Use Export Script |
43
+ | TextEncoder_Quantized | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 10.875 ms | 0 - 3 MB | NPU | Use Export Script |
44
+ | UNet_Quantized | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 258.151 ms | 13 - 15 MB | NPU | Use Export Script |
45
+ | UNet_Quantized | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 197.629 ms | 13 - 31 MB | NPU | Use Export Script |
46
+ | UNet_Quantized | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 256.936 ms | 13 - 16 MB | NPU | Use Export Script |
47
+ | VAEDecoder_Quantized | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 397.625 ms | 0 - 2 MB | NPU | Use Export Script |
48
+ | VAEDecoder_Quantized | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 300.627 ms | 0 - 21 MB | NPU | Use Export Script |
49
+ | VAEDecoder_Quantized | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 395.006 ms | 0 - 3 MB | NPU | Use Export Script |
50
+ | ControlNet_Quantized | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 104.668 ms | 2 - 9 MB | NPU | Use Export Script |
51
+ | ControlNet_Quantized | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 77.289 ms | 2 - 23 MB | NPU | Use Export Script |
52
+ | ControlNet_Quantized | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 103.817 ms | 2 - 5 MB | NPU | Use Export Script |
53
 
54
 
55
 
 
111
  Profiling Results
112
  ------------------------------------------------------------
113
  TextEncoder_Quantized
114
+ Device : cs_8_gen_2 (ANDROID 13)
115
+ Runtime : QNN
116
+ Estimated inference time (ms) : 10.9
117
+ Estimated peak memory usage (MB): [0, 3]
118
+ Total # Ops : 569
119
+ Compute Unit(s) : npu (569 ops) gpu (0 ops) cpu (0 ops)
120
 
121
  ------------------------------------------------------------
122
  UNet_Quantized
123
+ Device : cs_8_gen_2 (ANDROID 13)
124
+ Runtime : QNN
125
+ Estimated inference time (ms) : 258.2
126
+ Estimated peak memory usage (MB): [13, 15]
127
+ Total # Ops : 5433
128
+ Compute Unit(s) : npu (5433 ops) gpu (0 ops) cpu (0 ops)
129
 
130
  ------------------------------------------------------------
131
  VAEDecoder_Quantized
132
+ Device : cs_8_gen_2 (ANDROID 13)
133
+ Runtime : QNN
134
+ Estimated inference time (ms) : 397.6
135
+ Estimated peak memory usage (MB): [0, 2]
136
+ Total # Ops : 408
137
+ Compute Unit(s) : npu (408 ops) gpu (0 ops) cpu (0 ops)
138
 
139
  ------------------------------------------------------------
140
  ControlNet_Quantized
141
+ Device : cs_8_gen_2 (ANDROID 13)
142
+ Runtime : QNN
143
+ Estimated inference time (ms) : 104.7
144
+ Estimated peak memory usage (MB): [2, 9]
145
+ Total # Ops : 2405
146
+ Compute Unit(s) : npu (2405 ops) gpu (0 ops) cpu (0 ops)
147
  ```
148
 
149
 
TextEncoder_Quantized.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4355278c27482577083f4afdec02b783d9d43fd9d349226265cbe455de6764d2
3
- size 162623336
 
 
 
 
TextEncoder_Quantized.so DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4355278c27482577083f4afdec02b783d9d43fd9d349226265cbe455de6764d2
3
- size 162623336
 
 
 
 
UNet_Quantized.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a541970e46808e9d65337db4ff83022376d4acb35cb8159555b22fb65d92a0a3
3
- size 880611000
 
 
 
 
UNet_Quantized.so DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a541970e46808e9d65337db4ff83022376d4acb35cb8159555b22fb65d92a0a3
3
- size 880611000
 
 
 
 
VAEDecoder_Quantized.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5583d793b155115acfc74e32bdf87951519c5bf9f0675d177bf6d474edab1c0c
3
- size 72766264
 
 
 
 
VAEDecoder_Quantized.so DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5583d793b155115acfc74e32bdf87951519c5bf9f0675d177bf6d474edab1c0c
3
- size 72766264