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™ 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™ 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	1.517 ms	1 - 1 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X Elite	3.428 ms	157 - 157 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	2.298 ms	0 - 14 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.247 ms	0 - 162 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	3.335 ms	0 - 3 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	3.428 ms	157 - 157 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	25.613 ms	0 - 10 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	3.675 ms	0 - 6 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	1.75 ms	0 - 7 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Mobile	1.75 ms	0 - 7 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.542 ms	0 - 11 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	3.675 ms	0 - 6 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X2 Elite	1.769 ms	1 - 1 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X Elite	3.612 ms	0 - 0 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 3 Mobile	2.32 ms	0 - 7 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ QCS8275	7.466 ms	0 - 9 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.244 ms	0 - 1 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8775P	3.487 ms	0 - 5 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8650P	3.487 ms	0 - 5 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8255P	3.487 ms	0 - 5 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-9075	3.318 ms	0 - 2 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-X7181	3.612 ms	0 - 0 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-6690	24.117 ms	0 - 6 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-7790	3.665 ms	0 - 6 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-8750	1.754 ms	0 - 13 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA7255P	7.466 ms	0 - 9 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Mobile	1.754 ms	0 - 13 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.548 ms	0 - 9 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 7 Gen 4 Mobile	3.665 ms	0 - 6 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X2 Elite	46.316 ms	1 - 1 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X Elite	113.599 ms	843 - 843 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	80.741 ms	1 - 12 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	113.9 ms	0 - 898 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	105.698 ms	0 - 3 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	113.599 ms	843 - 843 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	2239.725 ms	1 - 11 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	178.115 ms	0 - 11 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	61.717 ms	0 - 11 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Mobile	61.717 ms	0 - 11 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	47.791 ms	0 - 12 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	178.115 ms	0 - 11 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X2 Elite	46.482 ms	0 - 0 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X Elite	113.842 ms	0 - 0 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 3 Mobile	80.609 ms	14 - 20 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ QCS8275	262.571 ms	0 - 10 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	113.278 ms	1 - 2 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8775P	105.963 ms	0 - 9 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8650P	105.963 ms	0 - 9 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8255P	105.963 ms	0 - 9 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-9075	105.772 ms	2 - 4 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-X7181	113.842 ms	0 - 0 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-6690	1993.704 ms	0 - 7 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-7790	177.846 ms	0 - 6 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-8750	58.995 ms	1 - 10 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA7255P	262.571 ms	0 - 10 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Mobile	58.995 ms	1 - 10 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	45.936 ms	0 - 9 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 7 Gen 4 Mobile	177.846 ms	0 - 6 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X2 Elite	127.3 ms	4 - 4 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X Elite	257.362 ms	62 - 62 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	197.255 ms	3 - 16 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	261.324 ms	4 - 5 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	240.491 ms	3 - 6 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	257.362 ms	62 - 62 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	6341.169 ms	4 - 10 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	505.877 ms	2 - 7 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	171.137 ms	4 - 10 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Mobile	171.137 ms	4 - 10 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	121.904 ms	3 - 10 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	505.877 ms	2 - 7 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X2 Elite	127.494 ms	0 - 0 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X Elite	257.798 ms	0 - 0 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 3 Mobile	196.367 ms	0 - 7 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ QCS8275	711.84 ms	0 - 9 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	260.731 ms	1 - 3 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8775P	243.881 ms	0 - 10 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8650P	243.881 ms	0 - 10 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8255P	243.881 ms	0 - 10 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-9075	240.398 ms	2 - 5 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-X7181	257.798 ms	0 - 0 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-6690	6222.56 ms	3 - 10 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-7790	504.887 ms	1 - 7 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-8750	172.765 ms	0 - 13 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA7255P	711.84 ms	0 - 9 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Mobile	172.765 ms	0 - 13 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	120.035 ms	0 - 9 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 7 Gen 4 Mobile	504.887 ms	1 - 7 MB	NPU

License

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

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

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

Unconditional Image Generation

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/Stable-Diffusion-v1.5

High-Resolution Image Synthesis with Latent Diffusion Models

Paper • 2112.10752 • Published Dec 20, 2021 • 17