Stable-Diffusion-v1.5: 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-v1.5 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® X Elite	QAIRT 2.37, ONNX Runtime 1.23.0	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	QAIRT 2.37, ONNX Runtime 1.23.0	Download
PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	QAIRT 2.37, ONNX Runtime 1.23.0	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	QAIRT 2.37, ONNX Runtime 1.23.0	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	QAIRT 2.37, ONNX Runtime 1.23.0	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	QAIRT 2.37, ONNX Runtime 1.23.0	Download
PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCM6690	QAIRT 2.37, ONNX Runtime 1.23.0	Download
PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCS9075	QAIRT 2.37, ONNX Runtime 1.23.0	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® X Elite	QAIRT 2.42	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 3 Mobile	QAIRT 2.42	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS8275 (Proxy)	QAIRT 2.42	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS8550 (Proxy)	QAIRT 2.42	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8775P	QAIRT 2.42	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	QAIRT 2.42	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® 7 Gen 4 Mobile	QAIRT 2.42	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	QAIRT 2.42	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA7255P	QAIRT 2.42	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCM6690	QAIRT 2.42	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS9075	QAIRT 2.42	Download

For more device-specific assets and performance metrics, visit Stable-Diffusion-v1.5 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-v1.5 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® X Elite	5.64 ms	157 - 157 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	3.958 ms	0 - 10 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	5.472 ms	6 - 167 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCS9075	5.453 ms	0 - 3 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCM6690	28.045 ms	0 - 10 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	3.126 ms	0 - 12 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	5.812 ms	0 - 7 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	2.621 ms	0 - 10 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X Elite	3.607 ms	0 - 0 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 3 Mobile	2.275 ms	0 - 7 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS8275 (Proxy)	7.566 ms	0 - 8 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS8550 (Proxy)	3.24 ms	0 - 2 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8775P	3.486 ms	0 - 9 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS9075	3.307 ms	2 - 4 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCM6690	22.203 ms	0 - 6 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA7255P	7.566 ms	0 - 8 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.759 ms	0 - 13 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 7 Gen 4 Mobile	3.629 ms	0 - 6 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.493 ms	0 - 9 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X Elite	113.396 ms	842 - 842 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	81.37 ms	0 - 13 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	113.054 ms	1 - 899 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCS9075	107.446 ms	0 - 3 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCM6690	2188.746 ms	0 - 11 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	64.237 ms	0 - 13 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	172.335 ms	0 - 11 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	44.91 ms	0 - 8 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X Elite	112.945 ms	0 - 0 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 3 Mobile	79.077 ms	0 - 7 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS8275 (Proxy)	262.503 ms	0 - 7 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS8550 (Proxy)	112.133 ms	0 - 2 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8775P	105.509 ms	0 - 7 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS9075	105.026 ms	0 - 2 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCM6690	2211.419 ms	0 - 11 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA7255P	262.503 ms	0 - 7 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	60.171 ms	0 - 13 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 7 Gen 4 Mobile	183.924 ms	0 - 6 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	44.845 ms	0 - 10 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X Elite	218.035 ms	59 - 59 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	163.458 ms	5 - 13 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	219.135 ms	1 - 66 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCS9075	206.405 ms	3 - 6 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCM6690	5423.617 ms	0 - 7 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	146.897 ms	4 - 10 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	445.272 ms	3 - 10 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	90.54 ms	3 - 14 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X Elite	264.468 ms	0 - 0 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 3 Mobile	203.237 ms	0 - 8 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS8275 (Proxy)	725.4 ms	0 - 9 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS8550 (Proxy)	269.843 ms	1 - 2 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8775P	253.004 ms	0 - 9 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS9075	250.279 ms	0 - 3 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCM6690	6335.72 ms	1 - 7 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA7255P	725.4 ms	0 - 9 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	180.005 ms	0 - 9 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 7 Gen 4 Mobile	512.113 ms	0 - 6 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	116.863 ms	0 - 9 MB	NPU

License

• The license for the original implementation of Stable-Diffusion-v1.5 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