Stable-Diffusion-v2.1: Optimized for Qualcomm Devices

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 is based on the implementation of Stable-Diffusion-v2.1 found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

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.

Getting Started

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime	Precision	Chipset	SDK Versions	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	QAIRT 2.42, ONNX Runtime 1.24.3	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X2 Elite	QAIRT 2.42, ONNX Runtime 1.24.3	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X Elite	QAIRT 2.42, ONNX Runtime 1.24.3	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	QAIRT 2.42, ONNX Runtime 1.24.3	Download
PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	QAIRT 2.42, ONNX Runtime 1.24.3	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	QAIRT 2.42, ONNX Runtime 1.24.3	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	QAIRT 2.42, ONNX Runtime 1.24.3	Download
PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCM6690	QAIRT 2.42, ONNX Runtime 1.24.3	Download
PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCS9075	QAIRT 2.42, ONNX Runtime 1.24.3	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® X2 Elite	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® X Elite	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 3 Mobile	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS8550 (Proxy)	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8775P	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® 7 Gen 4 Mobile	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA7255P	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCM6690	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS9075	QAIRT 2.45	Download

For more device-specific assets and performance metrics, visit Stable-Diffusion-v2.1 on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

• Custom weights (e.g., fine-tuned checkpoints)
• Custom input shapes
• Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for Stable-Diffusion-v2.1 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_generation

Model Stats:

• Input: Text prompt to generate image

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	4.625 ms	0 - 10 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X2 Elite	3.282 ms	417 - 417 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X Elite	7.722 ms	418 - 418 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	5.972 ms	1 - 11 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	7.968 ms	0 - 450 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCS9075	7.396 ms	0 - 3 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCM6690	68.77 ms	0 - 10 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	5.065 ms	0 - 12 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	12.059 ms	0 - 10 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	4.831 ms	0 - 10 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X2 Elite	4.187 ms	0 - 0 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X Elite	7.843 ms	0 - 0 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 3 Mobile	5.821 ms	0 - 8 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS8275 (Proxy)	17.365 ms	0 - 7 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS8550 (Proxy)	8.075 ms	0 - 2 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8775P	8.338 ms	0 - 8 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS9075	8.057 ms	2 - 4 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCM6690	68.812 ms	0 - 6 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA7255P	17.365 ms	0 - 7 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	4.933 ms	0 - 9 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 7 Gen 4 Mobile	12.117 ms	0 - 6 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	70.359 ms	0 - 8 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X2 Elite	66.133 ms	843 - 843 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X Elite	157.72 ms	842 - 842 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	111.382 ms	0 - 12 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	153.43 ms	0 - 898 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCS9075	149.144 ms	0 - 3 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCM6690	2350.728 ms	0 - 11 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	101.214 ms	1 - 12 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	217.21 ms	0 - 11 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	64.774 ms	0 - 9 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X2 Elite	68.04 ms	0 - 0 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X Elite	157.543 ms	0 - 0 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 3 Mobile	110.096 ms	0 - 7 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS8275 (Proxy)	345.961 ms	0 - 7 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS8550 (Proxy)	152.579 ms	0 - 3 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8775P	147.813 ms	0 - 8 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS9075	146.877 ms	0 - 2 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCM6690	2404.858 ms	1 - 10 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA7255P	345.961 ms	0 - 7 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	98.46 ms	0 - 9 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 7 Gen 4 Mobile	210.948 ms	0 - 7 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	136.058 ms	3 - 13 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X2 Elite	144.455 ms	63 - 63 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X Elite	260.328 ms	64 - 64 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	198.464 ms	3 - 10 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	262.159 ms	0 - 66 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCS9075	246.802 ms	4 - 6 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCM6690	6282.127 ms	23 - 29 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	172.732 ms	3 - 15 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	507.588 ms	2 - 8 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	121.204 ms	0 - 10 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X2 Elite	228.427 ms	0 - 0 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X Elite	257.579 ms	0 - 0 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 3 Mobile	195.85 ms	0 - 8 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS8275 (Proxy)	713.024 ms	0 - 9 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS8550 (Proxy)	260.197 ms	1 - 2 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8775P	244.482 ms	0 - 9 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS9075	242.073 ms	2 - 5 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCM6690	6269.035 ms	0 - 7 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA7255P	713.024 ms	0 - 9 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	159.535 ms	0 - 13 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 7 Gen 4 Mobile	504.565 ms	1 - 7 MB	NPU

License

• The license for the original implementation of Stable-Diffusion-v2.1 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.

Usage and Limitations

This model may not be used for or in connection with any of the following applications:

• Accessing essential private and public services and benefits;
• Administration of justice and democratic processes;
• Assessing or recognizing the emotional state of a person;
• Biometric and biometrics-based systems, including categorization of persons based on sensitive characteristics;
• Education and vocational training;
• Employment and workers management;
• Exploitation of the vulnerabilities of persons resulting in harmful behavior;
• General purpose social scoring;
• Law enforcement;
• Management and operation of critical infrastructure;
• Migration, asylum and border control management;
• Predictive policing;
• Real-time remote biometric identification in public spaces;
• Recommender systems of social media platforms;
• Scraping of facial images (from the internet or otherwise); and/or
• Subliminal manipulation