Stable-Diffusion-v1.5: Optimized for Mobile Deployment

State-of-the-art generative AI model used to generate detailed images conditioned on text descriptions

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.

This model is an implementation of Stable-Diffusion-v1.5 found here.

This repository provides scripts to run Stable-Diffusion-v1.5 on Qualcomm® devices. More details on model performance across various devices, can be found here.

Model Details

Model Type: Model_use_case.image_generation
Model Stats:
- Input: Text prompt to generate image

Model	Precision	Device	Chipset	Target Runtime	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit	Target Model
text_encoder	w8a16	QCS8275 (Proxy)	Qualcomm® QCS8275 (Proxy)	QNN_CONTEXT_BINARY	11.062 ms	0 - 9 MB	NPU	Use Export Script
text_encoder	w8a16	QCS8550 (Proxy)	Qualcomm® QCS8550 (Proxy)	QNN_CONTEXT_BINARY	5.434 ms	0 - 4 MB	NPU	Use Export Script
text_encoder	w8a16	QCS9075 (Proxy)	Qualcomm® QCS9075 (Proxy)	QNN_CONTEXT_BINARY	5.897 ms	0 - 10 MB	NPU	Use Export Script
text_encoder	w8a16	SA7255P ADP	Qualcomm® SA7255P	QNN_CONTEXT_BINARY	11.062 ms	0 - 9 MB	NPU	Use Export Script
text_encoder	w8a16	SA8255 (Proxy)	Qualcomm® SA8255P (Proxy)	QNN_CONTEXT_BINARY	5.404 ms	0 - 2 MB	NPU	Use Export Script
text_encoder	w8a16	SA8650 (Proxy)	Qualcomm® SA8650P (Proxy)	QNN_CONTEXT_BINARY	5.383 ms	0 - 4 MB	NPU	Use Export Script
text_encoder	w8a16	SA8775P ADP	Qualcomm® SA8775P	QNN_CONTEXT_BINARY	5.897 ms	0 - 10 MB	NPU	Use Export Script
text_encoder	w8a16	Samsung Galaxy S23	Snapdragon® 8 Gen 2 Mobile	QNN_CONTEXT_BINARY	5.388 ms	0 - 2 MB	NPU	Use Export Script
text_encoder	w8a16	Samsung Galaxy S23	Snapdragon® 8 Gen 2 Mobile	PRECOMPILED_QNN_ONNX	5.707 ms	0 - 162 MB	NPU	Use Export Script
text_encoder	w8a16	Samsung Galaxy S24	Snapdragon® 8 Gen 3 Mobile	QNN_CONTEXT_BINARY	3.884 ms	0 - 18 MB	NPU	Use Export Script
text_encoder	w8a16	Samsung Galaxy S24	Snapdragon® 8 Gen 3 Mobile	PRECOMPILED_QNN_ONNX	4.116 ms	0 - 19 MB	NPU	Use Export Script
text_encoder	w8a16	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite Mobile	QNN_CONTEXT_BINARY	3.504 ms	0 - 15 MB	NPU	Use Export Script
text_encoder	w8a16	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite Mobile	PRECOMPILED_QNN_ONNX	3.846 ms	0 - 14 MB	NPU	Use Export Script
text_encoder	w8a16	Snapdragon X Elite CRD	Snapdragon® X Elite	QNN_CONTEXT_BINARY	5.842 ms	1 - 1 MB	NPU	Use Export Script
text_encoder	w8a16	Snapdragon X Elite CRD	Snapdragon® X Elite	PRECOMPILED_QNN_ONNX	5.942 ms	157 - 157 MB	NPU	Use Export Script
unet	w8a16	QCS8275 (Proxy)	Qualcomm® QCS8275 (Proxy)	QNN_CONTEXT_BINARY	263.519 ms	0 - 7 MB	NPU	Use Export Script
unet	w8a16	QCS8550 (Proxy)	Qualcomm® QCS8550 (Proxy)	QNN_CONTEXT_BINARY	111.179 ms	0 - 2 MB	NPU	Use Export Script
unet	w8a16	QCS9075 (Proxy)	Qualcomm® QCS9075 (Proxy)	QNN_CONTEXT_BINARY	105.264 ms	0 - 8 MB	NPU	Use Export Script
unet	w8a16	SA7255P ADP	Qualcomm® SA7255P	QNN_CONTEXT_BINARY	263.519 ms	0 - 7 MB	NPU	Use Export Script
unet	w8a16	SA8255 (Proxy)	Qualcomm® SA8255P (Proxy)	QNN_CONTEXT_BINARY	111.759 ms	0 - 2 MB	NPU	Use Export Script
unet	w8a16	SA8650 (Proxy)	Qualcomm® SA8650P (Proxy)	QNN_CONTEXT_BINARY	112.295 ms	0 - 2 MB	NPU	Use Export Script
unet	w8a16	SA8775P ADP	Qualcomm® SA8775P	QNN_CONTEXT_BINARY	105.264 ms	0 - 8 MB	NPU	Use Export Script
unet	w8a16	Samsung Galaxy S23	Snapdragon® 8 Gen 2 Mobile	QNN_CONTEXT_BINARY	110.854 ms	0 - 2 MB	NPU	Use Export Script
unet	w8a16	Samsung Galaxy S23	Snapdragon® 8 Gen 2 Mobile	PRECOMPILED_QNN_ONNX	112.905 ms	0 - 898 MB	NPU	Use Export Script
unet	w8a16	Samsung Galaxy S24	Snapdragon® 8 Gen 3 Mobile	QNN_CONTEXT_BINARY	77.505 ms	0 - 17 MB	NPU	Use Export Script
unet	w8a16	Samsung Galaxy S24	Snapdragon® 8 Gen 3 Mobile	PRECOMPILED_QNN_ONNX	79.744 ms	0 - 16 MB	NPU	Use Export Script
unet	w8a16	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite Mobile	QNN_CONTEXT_BINARY	68.211 ms	0 - 15 MB	NPU	Use Export Script
unet	w8a16	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite Mobile	PRECOMPILED_QNN_ONNX	59.789 ms	0 - 19 MB	NPU	Use Export Script
unet	w8a16	Snapdragon X Elite CRD	Snapdragon® X Elite	QNN_CONTEXT_BINARY	113.189 ms	0 - 0 MB	NPU	Use Export Script
unet	w8a16	Snapdragon X Elite CRD	Snapdragon® X Elite	PRECOMPILED_QNN_ONNX	114.173 ms	842 - 842 MB	NPU	Use Export Script
vae	w8a16	QCS8275 (Proxy)	Qualcomm® QCS8275 (Proxy)	QNN_CONTEXT_BINARY	719.119 ms	0 - 9 MB	NPU	Use Export Script
vae	w8a16	QCS8550 (Proxy)	Qualcomm® QCS8550 (Proxy)	QNN_CONTEXT_BINARY	269.222 ms	0 - 3 MB	NPU	Use Export Script
vae	w8a16	QCS9075 (Proxy)	Qualcomm® QCS9075 (Proxy)	QNN_CONTEXT_BINARY	249.106 ms	0 - 10 MB	NPU	Use Export Script
vae	w8a16	SA7255P ADP	Qualcomm® SA7255P	QNN_CONTEXT_BINARY	719.119 ms	0 - 9 MB	NPU	Use Export Script
vae	w8a16	SA8255 (Proxy)	Qualcomm® SA8255P (Proxy)	QNN_CONTEXT_BINARY	271.482 ms	0 - 3 MB	NPU	Use Export Script
vae	w8a16	SA8650 (Proxy)	Qualcomm® SA8650P (Proxy)	QNN_CONTEXT_BINARY	272.149 ms	0 - 2 MB	NPU	Use Export Script
vae	w8a16	SA8775P ADP	Qualcomm® SA8775P	QNN_CONTEXT_BINARY	249.106 ms	0 - 10 MB	NPU	Use Export Script
vae	w8a16	Samsung Galaxy S23	Snapdragon® 8 Gen 2 Mobile	QNN_CONTEXT_BINARY	269.96 ms	0 - 3 MB	NPU	Use Export Script
vae	w8a16	Samsung Galaxy S23	Snapdragon® 8 Gen 2 Mobile	PRECOMPILED_QNN_ONNX	274.29 ms	0 - 66 MB	NPU	Use Export Script
vae	w8a16	Samsung Galaxy S24	Snapdragon® 8 Gen 3 Mobile	QNN_CONTEXT_BINARY	204.3 ms	0 - 18 MB	NPU	Use Export Script
vae	w8a16	Samsung Galaxy S24	Snapdragon® 8 Gen 3 Mobile	PRECOMPILED_QNN_ONNX	204.75 ms	3 - 21 MB	NPU	Use Export Script
vae	w8a16	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite Mobile	QNN_CONTEXT_BINARY	194.981 ms	0 - 14 MB	NPU	Use Export Script
vae	w8a16	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite Mobile	PRECOMPILED_QNN_ONNX	193.913 ms	3 - 17 MB	NPU	Use Export Script
vae	w8a16	Snapdragon X Elite CRD	Snapdragon® X Elite	QNN_CONTEXT_BINARY	265.408 ms	0 - 0 MB	NPU	Use Export Script
vae	w8a16	Snapdragon X Elite CRD	Snapdragon® X Elite	PRECOMPILED_QNN_ONNX	264.914 ms	63 - 63 MB	NPU	Use Export Script

Deploy to Snapdragon X Elite NPU

Please follow the Stable Diffusion Windows App tutorial to quantize model with custom weights.

Quantize and Deploy Your Own Fine-Tuned Stable Diffusion

Please follow the Quantize Stable Diffusion tutorial to quantize model with custom weights.

Installation

Install the package via pip:

pip install "qai-hub-models[stable-diffusion-v1-5]"

Configure Qualcomm® AI Hub to run this model on a cloud-hosted device

Sign-in to Qualcomm® AI Hub with your Qualcomm® ID. Once signed in navigate to Account -> Settings -> API Token.

With this API token, you can configure your client to run models on the cloud hosted devices.

qai-hub configure --api_token API_TOKEN

Navigate to docs for more information.

Demo off target

The package contains a simple end-to-end demo that downloads pre-trained weights and runs this model on a sample input.

python -m qai_hub_models.models.stable_diffusion_v1_5.demo

The above demo runs a reference implementation of pre-processing, model inference, and post processing.

NOTE: If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above).

%run -m qai_hub_models.models.stable_diffusion_v1_5.demo

Run model on a cloud-hosted device

In addition to the demo, you can also run the model on a cloud-hosted Qualcomm® device. This script does the following:

Performance check on-device on a cloud-hosted device
Downloads compiled assets that can be deployed on-device for Android.
Accuracy check between PyTorch and on-device outputs.

python -m qai_hub_models.models.stable_diffusion_v1_5.export

Profiling Results
------------------------------------------------------------
text_encoder
Device                          : cs_8275 (ANDROID 14)                 
Runtime                         : QNN_CONTEXT_BINARY                   
Estimated inference time (ms)   : 11.1                                 
Estimated peak memory usage (MB): [0, 9]                               
Total # Ops                     : 438                                  
Compute Unit(s)                 : npu (438 ops) gpu (0 ops) cpu (0 ops)

------------------------------------------------------------
unet
Device                          : cs_8275 (ANDROID 14)                  
Runtime                         : QNN_CONTEXT_BINARY                    
Estimated inference time (ms)   : 263.5                                 
Estimated peak memory usage (MB): [0, 7]                                
Total # Ops                     : 4042                                  
Compute Unit(s)                 : npu (4042 ops) gpu (0 ops) cpu (0 ops)

------------------------------------------------------------
vae
Device                          : cs_8275 (ANDROID 14)                 
Runtime                         : QNN_CONTEXT_BINARY                   
Estimated inference time (ms)   : 719.1                                
Estimated peak memory usage (MB): [0, 9]                               
Total # Ops                     : 175                                  
Compute Unit(s)                 : npu (175 ops) gpu (0 ops) cpu (0 ops)

Deploying compiled model to Android

The models can be deployed using multiple runtimes:

TensorFlow Lite (.tflite export): This tutorial provides a guide to deploy the .tflite model in an Android application.
QNN (.so export ): This sample app provides instructions on how to use the .so shared library in an Android application.

View on Qualcomm® AI Hub

Get more details on Stable-Diffusion-v1.5's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

The license for the original implementation of Stable-Diffusion-v1.5 can be found here.
The license for the compiled assets for on-device deployment can be found here

References

Community

Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
For questions or feedback please reach out to us.