Hugging Face's logo

gamehiro
/
Stable-Diffusion-v2.1

Unconditional Image Generation
PyTorch
generative_ai
android
Model card Files
xet
 Community
gamehiro qaihm-bot commited on
Commit
e5a9386
·
0 Parent(s):

Duplicate from qualcomm/Stable-Diffusion-v2.1

Browse files

Co-authored-by: QAIHM Bot <qaihm-bot@users.noreply.huggingface.co>

Files changed (3) hide show
  1. .gitattributes +36 -0
  2. LICENSE +1 -0
  3. README.md +178 -0
.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ VaeDecoderQuantizable.so filter=lfs diff=lfs merge=lfs -text
LICENSE ADDED
@@ -0,0 +1 @@
 
 
1
+ The license of the original trained model can be found at https://github.com/CompVis/stable-diffusion/blob/main/LICENSE.
README.md ADDED
@@ -0,0 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: pytorch
3
+ license: other
4
+ tags:
5
+ - generative_ai
6
+ - android
7
+ pipeline_tag: unconditional-image-generation
8
+
9
+ ---
10
+
11
+ ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stable_diffusion_v2_1/web-assets/model_demo.png)
12
+
13
+ # Stable-Diffusion-v2.1: Optimized for Qualcomm Devices
14
+
15
+ Generates high resolution images from text prompts using a latent diffusion model. This model uses CLIP ViT-L/14 as text encoder, U-Net based latent denoising, and VAE based decoder to generate the final image.
16
+
17
+ This is based on the implementation of Stable-Diffusion-v2.1 found [here](https://github.com/CompVis/stable-diffusion/tree/main).
18
+ This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/stable_diffusion_v2_1) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
19
+
20
+ Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
21
+
22
+ ## Deploy to Snapdragon X Elite NPU
23
+ 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.
24
+
25
+ ## Quantize and Deploy Your Own Fine-Tuned Stable Diffusion
26
+
27
+ Please follow the [Quantize Stable Diffusion]({REPOSITORY_URL}/tutorials/stable_diffusion/quantize_stable_diffusion.md) tutorial to quantize model with custom weights.
28
+
29
+ ## Getting Started
30
+ There are two ways to deploy this model on your device:
31
+
32
+ ### Option 1: Download Pre-Exported Models
33
+
34
+ Below are pre-exported model assets ready for deployment.
35
+
36
+ | Runtime | Precision | Chipset | SDK Versions | Download |
37
+ |---|---|---|---|---|
38
+ | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stable_diffusion_v2_1/releases/v0.48.0/stable_diffusion_v2_1-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_x2_elite.zip)
39
+ | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stable_diffusion_v2_1/releases/v0.48.0/stable_diffusion_v2_1-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_x_elite.zip)
40
+ | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stable_diffusion_v2_1/releases/v0.48.0/stable_diffusion_v2_1-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8gen3.zip)
41
+ | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stable_diffusion_v2_1/releases/v0.48.0/stable_diffusion_v2_1-precompiled_qnn_onnx-w8a16-qualcomm_qcs8550_proxy.zip)
42
+ | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stable_diffusion_v2_1/releases/v0.48.0/stable_diffusion_v2_1-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8_elite_for_galaxy.zip)
43
+ | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stable_diffusion_v2_1/releases/v0.48.0/stable_diffusion_v2_1-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_7gen4.zip)
44
+ | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stable_diffusion_v2_1/releases/v0.48.0/stable_diffusion_v2_1-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8_elite_gen5.zip)
45
+ | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCM6690 | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stable_diffusion_v2_1/releases/v0.48.0/stable_diffusion_v2_1-precompiled_qnn_onnx-w8a16-qualcomm_qcm6690.zip)
46
+ | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS9075 | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stable_diffusion_v2_1/releases/v0.48.0/stable_diffusion_v2_1-precompiled_qnn_onnx-w8a16-qualcomm_qcs9075.zip)
47
+ | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stable_diffusion_v2_1/releases/v0.48.0/stable_diffusion_v2_1-qnn_context_binary-w8a16-qualcomm_snapdragon_x2_elite.zip)
48
+ | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stable_diffusion_v2_1/releases/v0.48.0/stable_diffusion_v2_1-qnn_context_binary-w8a16-qualcomm_snapdragon_x_elite.zip)
49
+ | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stable_diffusion_v2_1/releases/v0.48.0/stable_diffusion_v2_1-qnn_context_binary-w8a16-qualcomm_snapdragon_8gen3.zip)
50
+ | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8550 (Proxy) | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stable_diffusion_v2_1/releases/v0.48.0/stable_diffusion_v2_1-qnn_context_binary-w8a16-qualcomm_qcs8550_proxy.zip)
51
+ | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stable_diffusion_v2_1/releases/v0.48.0/stable_diffusion_v2_1-qnn_context_binary-w8a16-qualcomm_sa8775p.zip)
52
+ | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stable_diffusion_v2_1/releases/v0.48.0/stable_diffusion_v2_1-qnn_context_binary-w8a16-qualcomm_snapdragon_8_elite_for_galaxy.zip)
53
+ | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stable_diffusion_v2_1/releases/v0.48.0/stable_diffusion_v2_1-qnn_context_binary-w8a16-qualcomm_snapdragon_7gen4.zip)
54
+ | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stable_diffusion_v2_1/releases/v0.48.0/stable_diffusion_v2_1-qnn_context_binary-w8a16-qualcomm_snapdragon_8_elite_gen5.zip)
55
+ | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stable_diffusion_v2_1/releases/v0.48.0/stable_diffusion_v2_1-qnn_context_binary-w8a16-qualcomm_sa7255p.zip)
56
+ | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCM6690 | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stable_diffusion_v2_1/releases/v0.48.0/stable_diffusion_v2_1-qnn_context_binary-w8a16-qualcomm_qcm6690.zip)
57
+ | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS9075 | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stable_diffusion_v2_1/releases/v0.48.0/stable_diffusion_v2_1-qnn_context_binary-w8a16-qualcomm_qcs9075.zip)
58
+
59
+ For more device-specific assets and performance metrics, visit **[Stable-Diffusion-v2.1 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/stable_diffusion_v2_1)**.
60
+
61
+
62
+ ### Option 2: Export with Custom Configurations
63
+
64
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/stable_diffusion_v2_1) Python library to compile and export the model with your own:
65
+ - Custom weights (e.g., fine-tuned checkpoints)
66
+ - Custom input shapes
67
+ - Target device and runtime configurations
68
+
69
+ This option is ideal if you need to customize the model beyond the default configuration provided here.
70
+
71
+ See our repository for [Stable-Diffusion-v2.1 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/stable_diffusion_v2_1) for usage instructions.
72
+
73
+ ## Model Details
74
+
75
+ **Model Type:** Model_use_case.image_generation
76
+
77
+ **Model Stats:**
78
+ - Input: Text prompt to generate image
79
+
80
+ ## Performance Summary
81
+ | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
82
+ |---|---|---|---|---|---|---
83
+ | text_encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 3.513 ms | 378 - 378 MB | NPU
84
+ | text_encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 8.344 ms | 378 - 378 MB | NPU
85
+ | text_encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.642 ms | 0 - 11 MB | NPU
86
+ | text_encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 7.965 ms | 0 - 386 MB | NPU
87
+ | text_encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS9075 | 7.986 ms | 0 - 3 MB | NPU
88
+ | text_encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCM6690 | 74.111 ms | 0 - 10 MB | NPU
89
+ | text_encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.626 ms | 0 - 7 MB | NPU
90
+ | text_encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 11.572 ms | 0 - 7 MB | NPU
91
+ | text_encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 4.294 ms | 0 - 10 MB | NPU
92
+ | text_encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 3.815 ms | 0 - 0 MB | NPU
93
+ | text_encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 8.258 ms | 0 - 0 MB | NPU
94
+ | text_encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.719 ms | 0 - 7 MB | NPU
95
+ | text_encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm�� QCS8275 (Proxy) | 18.684 ms | 0 - 8 MB | NPU
96
+ | text_encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8550 (Proxy) | 8.007 ms | 0 - 1 MB | NPU
97
+ | text_encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | 8.362 ms | 0 - 8 MB | NPU
98
+ | text_encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS9075 | 8.054 ms | 0 - 2 MB | NPU
99
+ | text_encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCM6690 | 72.011 ms | 0 - 6 MB | NPU
100
+ | text_encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | 18.684 ms | 0 - 8 MB | NPU
101
+ | text_encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.696 ms | 0 - 13 MB | NPU
102
+ | text_encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 11.593 ms | 0 - 6 MB | NPU
103
+ | text_encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 4.301 ms | 0 - 9 MB | NPU
104
+ | unet | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 40.18 ms | 845 - 845 MB | NPU
105
+ | unet | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 96.06 ms | 843 - 843 MB | NPU
106
+ | unet | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 69.984 ms | 0 - 11 MB | NPU
107
+ | unet | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 96.024 ms | 0 - 898 MB | NPU
108
+ | unet | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS9075 | 89.962 ms | 0 - 3 MB | NPU
109
+ | unet | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCM6690 | 2207.671 ms | 0 - 11 MB | NPU
110
+ | unet | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 55.839 ms | 0 - 11 MB | NPU
111
+ | unet | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 177.521 ms | 0 - 11 MB | NPU
112
+ | unet | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 38.417 ms | 0 - 9 MB | NPU
113
+ | unet | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 40.433 ms | 0 - 0 MB | NPU
114
+ | unet | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 96.801 ms | 0 - 0 MB | NPU
115
+ | unet | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 68.974 ms | 0 - 7 MB | NPU
116
+ | unet | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8275 (Proxy) | 233.267 ms | 0 - 7 MB | NPU
117
+ | unet | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8550 (Proxy) | 96.543 ms | 0 - 2 MB | NPU
118
+ | unet | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | 90.188 ms | 0 - 7 MB | NPU
119
+ | unet | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS9075 | 89.54 ms | 0 - 2 MB | NPU
120
+ | unet | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCM6690 | 2232.46 ms | 0 - 6 MB | NPU
121
+ | unet | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | 233.267 ms | 0 - 7 MB | NPU
122
+ | unet | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 53.753 ms | 1 - 9 MB | NPU
123
+ | unet | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 179.017 ms | 0 - 7 MB | NPU
124
+ | unet | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 39.84 ms | 0 - 9 MB | NPU
125
+ | vae | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 125.686 ms | 62 - 62 MB | NPU
126
+ | vae | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 264.42 ms | 62 - 62 MB | NPU
127
+ | vae | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 202.83 ms | 3 - 10 MB | NPU
128
+ | vae | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 266.85 ms | 0 - 66 MB | NPU
129
+ | vae | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS9075 | 249.575 ms | 3 - 6 MB | NPU
130
+ | vae | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCM6690 | 6283.129 ms | 1 - 7 MB | NPU
131
+ | vae | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 178.279 ms | 3 - 10 MB | NPU
132
+ | vae | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 514.308 ms | 2 - 8 MB | NPU
133
+ | vae | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 123.483 ms | 3 - 13 MB | NPU
134
+ | vae | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 133.374 ms | 0 - 0 MB | NPU
135
+ | vae | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 260.818 ms | 0 - 0 MB | NPU
136
+ | vae | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 202.09 ms | 0 - 8 MB | NPU
137
+ | vae | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8275 (Proxy) | 718.975 ms | 0 - 8 MB | NPU
138
+ | vae | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8550 (Proxy) | 264.333 ms | 0 - 2 MB | NPU
139
+ | vae | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | 250.394 ms | 0 - 9 MB | NPU
140
+ | vae | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS9075 | 247.568 ms | 0 - 3 MB | NPU
141
+ | vae | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCM6690 | 6352.675 ms | 0 - 6 MB | NPU
142
+ | vae | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | 718.975 ms | 0 - 8 MB | NPU
143
+ | vae | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 175.481 ms | 0 - 14 MB | NPU
144
+ | vae | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 514.429 ms | 0 - 6 MB | NPU
145
+ | vae | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 127.588 ms | 0 - 10 MB | NPU
146
+
147
+ ## License
148
+ * The license for the original implementation of Stable-Diffusion-v2.1 can be found
149
+ [here](https://github.com/CompVis/stable-diffusion/blob/main/LICENSE).
150
+
151
+ ## References
152
+ * [High-Resolution Image Synthesis with Latent Diffusion Models](https://arxiv.org/abs/2112.10752)
153
+ * [Source Model Implementation](https://github.com/CompVis/stable-diffusion/tree/main)
154
+
155
+ ## Community
156
+ * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
157
+ * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).
158
+
159
+ ## Usage and Limitations
160
+
161
+ This model may not be used for or in connection with any of the following applications:
162
+
163
+ - Accessing essential private and public services and benefits;
164
+ - Administration of justice and democratic processes;
165
+ - Assessing or recognizing the emotional state of a person;
166
+ - Biometric and biometrics-based systems, including categorization of persons based on sensitive characteristics;
167
+ - Education and vocational training;
168
+ - Employment and workers management;
169
+ - Exploitation of the vulnerabilities of persons resulting in harmful behavior;
170
+ - General purpose social scoring;
171
+ - Law enforcement;
172
+ - Management and operation of critical infrastructure;
173
+ - Migration, asylum and border control management;
174
+ - Predictive policing;
175
+ - Real-time remote biometric identification in public spaces;
176
+ - Recommender systems of social media platforms;
177
+ - Scraping of facial images (from the internet or otherwise); and/or
178
+ - Subliminal manipulation