Hugging Face's logo

qualcomm
/
Stable-Diffusion-v2.1

Unconditional Image Generation
PyTorch
generative_ai
quantized
android
Model card Files Community
1
shreyajn commited on
Commit
cf91919
·
verified ·
1 Parent(s): a05a13b

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +10 -10
README.md CHANGED
@@ -38,9 +38,9 @@ More details on model performance across various devices, can be found
38
 
39
  | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
40
  | ---|---|---|---|---|---|---|---|
41
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Binary | 11.661 ms | 0 - 1 MB | INT8 | NPU | [TextEncoder_Quantized.bin](https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/blob/main/TextEncoder_Quantized.bin)
42
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Binary | 216.843 ms | 0 - 2 MB | INT8 | NPU | [VAEDecoder_Quantized.bin](https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/blob/main/VAEDecoder_Quantized.bin)
43
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Binary | 97.301 ms | 0 - 2 MB | INT8 | NPU | [UNet_Quantized.bin](https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/blob/main/UNet_Quantized.bin)
44
 
45
 
46
 
@@ -103,23 +103,23 @@ python -m qai_hub_models.models.stable_diffusion_v2_1_quantized.export
103
  Profile Job summary of TextEncoder_Quantized
104
  --------------------------------------------------
105
  Device: Snapdragon X Elite CRD (11)
106
- Estimated Inference Time: 12.05 ms
107
  Estimated Peak Memory Range: 0.02-0.02 MB
108
  Compute Units: NPU (1040) | Total (1040)
109
 
110
  Profile Job summary of VAEDecoder_Quantized
111
  --------------------------------------------------
112
  Device: Snapdragon X Elite CRD (11)
113
- Estimated Inference Time: 220.43 ms
114
- Estimated Peak Memory Range: 0.07-0.07 MB
115
- Compute Units: NPU (172) | Total (172)
116
 
117
  Profile Job summary of UNet_Quantized
118
  --------------------------------------------------
119
  Device: Snapdragon X Elite CRD (11)
120
- Estimated Inference Time: 99.70 ms
121
- Estimated Peak Memory Range: 0.19-0.19 MB
122
- Compute Units: NPU (6363) | Total (6363)
123
 
124
 
125
  ```
 
38
 
39
  | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
40
  | ---|---|---|---|---|---|---|---|
41
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Binary | 11.701 ms | 0 - 1 MB | INT8 | NPU | [TextEncoder_Quantized.bin](https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/blob/main/TextEncoder_Quantized.bin)
42
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Binary | 216.248 ms | 0 - 1 MB | INT8 | NPU | [VAEDecoder_Quantized.bin](https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/blob/main/VAEDecoder_Quantized.bin)
43
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Binary | 100.062 ms | 0 - 2 MB | INT8 | NPU | [UNet_Quantized.bin](https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/blob/main/UNet_Quantized.bin)
44
 
45
 
46
 
 
103
  Profile Job summary of TextEncoder_Quantized
104
  --------------------------------------------------
105
  Device: Snapdragon X Elite CRD (11)
106
+ Estimated Inference Time: 11.80 ms
107
  Estimated Peak Memory Range: 0.02-0.02 MB
108
  Compute Units: NPU (1040) | Total (1040)
109
 
110
  Profile Job summary of VAEDecoder_Quantized
111
  --------------------------------------------------
112
  Device: Snapdragon X Elite CRD (11)
113
+ Estimated Inference Time: 220.25 ms
114
+ Estimated Peak Memory Range: 0.04-0.04 MB
115
+ Compute Units: NPU (170) | Total (170)
116
 
117
  Profile Job summary of UNet_Quantized
118
  --------------------------------------------------
119
  Device: Snapdragon X Elite CRD (11)
120
+ Estimated Inference Time: 102.50 ms
121
+ Estimated Peak Memory Range: 0.20-0.20 MB
122
+ Compute Units: NPU (6361) | Total (6361)
123
 
124
 
125
  ```