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® X2 Elite	QAIRT 2.45, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X Elite	QAIRT 2.45, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	QAIRT 2.45, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	QAIRT 2.45, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	QAIRT 2.45, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	QAIRT 2.45, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	QAIRT 2.45, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	QAIRT 2.45, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Mobile	QAIRT 2.45, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	QAIRT 2.45, ONNX Runtime 1.27.1	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® Dragonwing™ IQ-8275	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8775P	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-6690	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-9075	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA7255P	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® 7 Gen 4 Mobile	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Mobile	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	QAIRT 2.45	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® X2 Elite	1.514 ms	1 - 1 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X Elite	3.432 ms	156 - 156 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	2.309 ms	0 - 12 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	3.206 ms	0 - 4 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.242 ms	0 - 162 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	3.339 ms	0 - 3 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	3.432 ms	156 - 156 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	22.073 ms	0 - 10 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	3.688 ms	0 - 6 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	1.751 ms	0 - 13 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Mobile	1.751 ms	0 - 13 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.54 ms	0 - 11 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	3.688 ms	0 - 6 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X2 Elite	1.731 ms	1 - 1 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X Elite	3.636 ms	0 - 0 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 3 Mobile	2.318 ms	0 - 7 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-8275	3.189 ms	0 - 2 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.248 ms	0 - 1 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8775P	3.502 ms	0 - 9 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8650P	3.502 ms	0 - 9 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8255P	3.502 ms	0 - 9 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-9075	3.354 ms	0 - 2 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-X7181	3.636 ms	0 - 0 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-6690	23.32 ms	0 - 6 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-7790	3.676 ms	0 - 6 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-8750	1.752 ms	0 - 13 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA7255P	7.508 ms	0 - 10 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Mobile	1.752 ms	0 - 13 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.543 ms	0 - 13 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 7 Gen 4 Mobile	3.676 ms	0 - 6 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X2 Elite	46.251 ms	1 - 1 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X Elite	113.507 ms	843 - 843 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	81.307 ms	0 - 13 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	104.356 ms	0 - 4 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	112.55 ms	0 - 898 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	105.797 ms	0 - 3 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	113.507 ms	843 - 843 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	2259.227 ms	1 - 12 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	177.402 ms	0 - 12 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	61.487 ms	0 - 12 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Mobile	61.487 ms	0 - 12 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	51.109 ms	0 - 12 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	177.402 ms	0 - 12 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X2 Elite	46.515 ms	0 - 0 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X Elite	113.703 ms	0 - 0 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 3 Mobile	79.561 ms	0 - 7 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-8275	103.073 ms	0 - 3 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	112.527 ms	1 - 2 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8775P	106.166 ms	0 - 10 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8650P	106.166 ms	0 - 10 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8255P	106.166 ms	0 - 10 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-9075	105.081 ms	2 - 4 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-X7181	113.703 ms	0 - 0 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-6690	1887.838 ms	0 - 6 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-7790	177.816 ms	0 - 6 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-8750	60.348 ms	0 - 12 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA7255P	262.315 ms	0 - 10 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Mobile	60.348 ms	0 - 12 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	47.4 ms	0 - 8 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 7 Gen 4 Mobile	177.816 ms	0 - 6 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X2 Elite	128.705 ms	4 - 4 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X Elite	257.64 ms	61 - 61 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	197.108 ms	3 - 11 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	262.427 ms	3 - 7 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	260.308 ms	4 - 5 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	240.527 ms	3 - 6 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	257.64 ms	61 - 61 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	6234.474 ms	27 - 34 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	506.322 ms	2 - 8 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	170.847 ms	4 - 10 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Mobile	170.847 ms	4 - 10 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	120.006 ms	3 - 10 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	506.322 ms	2 - 8 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X2 Elite	127.123 ms	0 - 0 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X Elite	257.875 ms	0 - 0 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 3 Mobile	197.146 ms	1 - 8 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-8275	262.458 ms	0 - 4 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	259.337 ms	1 - 3 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8775P	243.877 ms	0 - 9 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8650P	243.877 ms	0 - 9 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8255P	243.877 ms	0 - 9 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-9075	240.745 ms	2 - 5 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-X7181	257.875 ms	0 - 0 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-6690	6196.809 ms	2 - 9 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-7790	505.684 ms	0 - 6 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-8750	170.855 ms	0 - 9 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA7255P	712.335 ms	0 - 10 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Mobile	170.855 ms	0 - 9 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	119.889 ms	0 - 10 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 7 Gen 4 Mobile	505.684 ms	0 - 6 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