Stable-Diffusion-v2.1: 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-v2.1 found here.

This repository provides scripts to run Stable-Diffusion-v2.1 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	18.419 ms	0 - 9 MB	NPU	Use Export Script
text_encoder	w8a16	QCS8550 (Proxy)	Qualcomm® QCS8550 (Proxy)	QNN_CONTEXT_BINARY	7.934 ms	0 - 3 MB	NPU	Use Export Script
text_encoder	w8a16	QCS8550 (Proxy)	Qualcomm® QCS8550 (Proxy)	PRECOMPILED_QNN_ONNX	7.796 ms	0 - 386 MB	NPU	Use Export Script
text_encoder	w8a16	QCS9075 (Proxy)	Qualcomm® QCS9075 (Proxy)	QNN_CONTEXT_BINARY	8.312 ms	0 - 9 MB	NPU	Use Export Script
text_encoder	w8a16	SA7255P ADP	Qualcomm® SA7255P	QNN_CONTEXT_BINARY	18.419 ms	0 - 9 MB	NPU	Use Export Script
text_encoder	w8a16	SA8255 (Proxy)	Qualcomm® SA8255P (Proxy)	QNN_CONTEXT_BINARY	7.948 ms	0 - 3 MB	NPU	Use Export Script
text_encoder	w8a16	SA8650 (Proxy)	Qualcomm® SA8650P (Proxy)	QNN_CONTEXT_BINARY	7.974 ms	1 - 3 MB	NPU	Use Export Script
text_encoder	w8a16	SA8775P ADP	Qualcomm® SA8775P	QNN_CONTEXT_BINARY	8.312 ms	0 - 9 MB	NPU	Use Export Script
text_encoder	w8a16	Samsung Galaxy S24	Snapdragon® 8 Gen 3 Mobile	QNN_CONTEXT_BINARY	5.365 ms	0 - 19 MB	NPU	Use Export Script
text_encoder	w8a16	Samsung Galaxy S24	Snapdragon® 8 Gen 3 Mobile	PRECOMPILED_QNN_ONNX	5.139 ms	0 - 19 MB	NPU	Use Export Script
text_encoder	w8a16	Samsung Galaxy S25	Snapdragon® 8 Elite For Galaxy Mobile	QNN_CONTEXT_BINARY	4.294 ms	0 - 17 MB	NPU	Use Export Script
text_encoder	w8a16	Samsung Galaxy S25	Snapdragon® 8 Elite For Galaxy Mobile	PRECOMPILED_QNN_ONNX	4.337 ms	0 - 13 MB	NPU	Use Export Script
text_encoder	w8a16	Snapdragon 8 Elite Gen 5 QRD	Snapdragon® 8 Elite Gen5 Mobile	QNN_CONTEXT_BINARY	4.28 ms	0 - 11 MB	NPU	Use Export Script
text_encoder	w8a16	Snapdragon 8 Elite Gen 5 QRD	Snapdragon® 8 Elite Gen5 Mobile	PRECOMPILED_QNN_ONNX	4.251 ms	0 - 14 MB	NPU	Use Export Script
text_encoder	w8a16	Snapdragon X Elite CRD	Snapdragon® X Elite	QNN_CONTEXT_BINARY	8.291 ms	0 - 0 MB	NPU	Use Export Script
text_encoder	w8a16	Snapdragon X Elite CRD	Snapdragon® X Elite	PRECOMPILED_QNN_ONNX	7.808 ms	379 - 379 MB	NPU	Use Export Script
unet	w8a16	QCS8275 (Proxy)	Qualcomm® QCS8275 (Proxy)	QNN_CONTEXT_BINARY	232.937 ms	0 - 8 MB	NPU	Use Export Script
unet	w8a16	QCS8550 (Proxy)	Qualcomm® QCS8550 (Proxy)	QNN_CONTEXT_BINARY	96.38 ms	0 - 3 MB	NPU	Use Export Script
unet	w8a16	QCS8550 (Proxy)	Qualcomm® QCS8550 (Proxy)	PRECOMPILED_QNN_ONNX	95.624 ms	0 - 898 MB	NPU	Use Export Script
unet	w8a16	QCS9075 (Proxy)	Qualcomm® QCS9075 (Proxy)	QNN_CONTEXT_BINARY	89.164 ms	0 - 8 MB	NPU	Use Export Script
unet	w8a16	SA7255P ADP	Qualcomm® SA7255P	QNN_CONTEXT_BINARY	232.937 ms	0 - 8 MB	NPU	Use Export Script
unet	w8a16	SA8255 (Proxy)	Qualcomm® SA8255P (Proxy)	QNN_CONTEXT_BINARY	96.552 ms	0 - 2 MB	NPU	Use Export Script
unet	w8a16	SA8650 (Proxy)	Qualcomm® SA8650P (Proxy)	QNN_CONTEXT_BINARY	96.049 ms	0 - 2 MB	NPU	Use Export Script
unet	w8a16	SA8775P ADP	Qualcomm® SA8775P	QNN_CONTEXT_BINARY	89.164 ms	0 - 8 MB	NPU	Use Export Script
unet	w8a16	Samsung Galaxy S24	Snapdragon® 8 Gen 3 Mobile	QNN_CONTEXT_BINARY	68.335 ms	0 - 19 MB	NPU	Use Export Script
unet	w8a16	Samsung Galaxy S24	Snapdragon® 8 Gen 3 Mobile	PRECOMPILED_QNN_ONNX	68.651 ms	0 - 16 MB	NPU	Use Export Script
unet	w8a16	Samsung Galaxy S25	Snapdragon® 8 Elite For Galaxy Mobile	QNN_CONTEXT_BINARY	54.913 ms	0 - 14 MB	NPU	Use Export Script
unet	w8a16	Samsung Galaxy S25	Snapdragon® 8 Elite For Galaxy Mobile	PRECOMPILED_QNN_ONNX	55.953 ms	0 - 11 MB	NPU	Use Export Script
unet	w8a16	Snapdragon 8 Elite Gen 5 QRD	Snapdragon® 8 Elite Gen5 Mobile	QNN_CONTEXT_BINARY	42.594 ms	0 - 11 MB	NPU	Use Export Script
unet	w8a16	Snapdragon 8 Elite Gen 5 QRD	Snapdragon® 8 Elite Gen5 Mobile	PRECOMPILED_QNN_ONNX	41.234 ms	0 - 7 MB	NPU	Use Export Script
unet	w8a16	Snapdragon X Elite CRD	Snapdragon® X Elite	QNN_CONTEXT_BINARY	95.869 ms	0 - 0 MB	NPU	Use Export Script
unet	w8a16	Snapdragon X Elite CRD	Snapdragon® X Elite	PRECOMPILED_QNN_ONNX	95.757 ms	843 - 843 MB	NPU	Use Export Script
vae	w8a16	QCS8275 (Proxy)	Qualcomm® QCS8275 (Proxy)	QNN_CONTEXT_BINARY	721.245 ms	0 - 9 MB	NPU	Use Export Script
vae	w8a16	QCS8550 (Proxy)	Qualcomm® QCS8550 (Proxy)	QNN_CONTEXT_BINARY	269.233 ms	0 - 3 MB	NPU	Use Export Script
vae	w8a16	QCS8550 (Proxy)	Qualcomm® QCS8550 (Proxy)	PRECOMPILED_QNN_ONNX	221.348 ms	3 - 6 MB	NPU	Use Export Script
vae	w8a16	QCS9075 (Proxy)	Qualcomm® QCS9075 (Proxy)	QNN_CONTEXT_BINARY	252.403 ms	1 - 10 MB	NPU	Use Export Script
vae	w8a16	SA7255P ADP	Qualcomm® SA7255P	QNN_CONTEXT_BINARY	721.245 ms	0 - 9 MB	NPU	Use Export Script
vae	w8a16	SA8255 (Proxy)	Qualcomm® SA8255P (Proxy)	QNN_CONTEXT_BINARY	267.093 ms	0 - 3 MB	NPU	Use Export Script
vae	w8a16	SA8650 (Proxy)	Qualcomm® SA8650P (Proxy)	QNN_CONTEXT_BINARY	270.458 ms	0 - 3 MB	NPU	Use Export Script
vae	w8a16	SA8775P ADP	Qualcomm® SA8775P	QNN_CONTEXT_BINARY	252.403 ms	1 - 10 MB	NPU	Use Export Script
vae	w8a16	Samsung Galaxy S24	Snapdragon® 8 Gen 3 Mobile	QNN_CONTEXT_BINARY	201.246 ms	0 - 19 MB	NPU	Use Export Script
vae	w8a16	Samsung Galaxy S24	Snapdragon® 8 Gen 3 Mobile	PRECOMPILED_QNN_ONNX	161.857 ms	3 - 22 MB	NPU	Use Export Script
vae	w8a16	Samsung Galaxy S25	Snapdragon® 8 Elite For Galaxy Mobile	QNN_CONTEXT_BINARY	176.589 ms	0 - 18 MB	NPU	Use Export Script
vae	w8a16	Samsung Galaxy S25	Snapdragon® 8 Elite For Galaxy Mobile	PRECOMPILED_QNN_ONNX	145.862 ms	3 - 17 MB	NPU	Use Export Script
vae	w8a16	Snapdragon 8 Elite Gen 5 QRD	Snapdragon® 8 Elite Gen5 Mobile	QNN_CONTEXT_BINARY	117.531 ms	0 - 11 MB	NPU	Use Export Script
vae	w8a16	Snapdragon 8 Elite Gen 5 QRD	Snapdragon® 8 Elite Gen5 Mobile	PRECOMPILED_QNN_ONNX	92.037 ms	3 - 14 MB	NPU	Use Export Script
vae	w8a16	Snapdragon X Elite CRD	Snapdragon® X Elite	QNN_CONTEXT_BINARY	264.316 ms	0 - 0 MB	NPU	Use Export Script
vae	w8a16	Snapdragon X Elite CRD	Snapdragon® X Elite	PRECOMPILED_QNN_ONNX	217.581 ms	59 - 59 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:

# NOTE: 3.10 <= PYTHON_VERSION < 3.14 is supported.
pip install "qai-hub-models[stable-diffusion-v2-1]"

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_v2_1.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_v2_1.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_v2_1.export

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-v2.1's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

• The license for the original implementation of Stable-Diffusion-v2.1 can be found here.
• The license for the compiled assets for on-device deployment can be found here

References

• High-Resolution Image Synthesis with Latent Diffusion Models
• Source Model Implementation

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.