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® 8 Elite Gen 5 For Galaxy Mobile	QAIRT 2.50, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	QAIRT 2.50, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X2 Elite	QAIRT 2.50, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X Elite	QAIRT 2.50, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	QAIRT 2.50, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	QAIRT 2.50, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	QAIRT 2.50, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	QAIRT 2.50, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	QAIRT 2.50, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	QAIRT 2.50, ONNX Runtime 1.27.1	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	QAIRT 2.50	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	QAIRT 2.50	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® X2 Elite	QAIRT 2.50	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® X Elite	QAIRT 2.50	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 3 Mobile	QAIRT 2.50	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-8275	QAIRT 2.50	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	QAIRT 2.50	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8775P	QAIRT 2.50	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-6690	QAIRT 2.50	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-9075	QAIRT 2.50	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA7255P	QAIRT 2.50	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® 7 Gen 4 Mobile	QAIRT 2.50	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® 8 Elite Gen 5 For Galaxy Mobile	1.551 ms	0 - 12 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.742 ms	0 - 13 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X2 Elite	1.607 ms	1 - 1 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X Elite	3.133 ms	156 - 156 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	2.207 ms	0 - 13 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	3.075 ms	0 - 4 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.05 ms	0 - 162 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	3.164 ms	0 - 3 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	3.133 ms	156 - 156 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	21.147 ms	0 - 11 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	3.3 ms	0 - 6 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	1.742 ms	0 - 13 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	3.3 ms	0 - 6 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	1.557 ms	0 - 9 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.738 ms	0 - 8 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X2 Elite	1.911 ms	0 - 0 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X Elite	3.36 ms	0 - 0 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 3 Mobile	2.21 ms	0 - 7 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-8275	3.051 ms	0 - 3 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.048 ms	0 - 2 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	3.156 ms	2 - 4 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-X7181	3.36 ms	0 - 0 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-6690	21.412 ms	0 - 6 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-7790	3.302 ms	0 - 6 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-8750	1.738 ms	0 - 8 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 7 Gen 4 Mobile	3.302 ms	0 - 6 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	48.21 ms	0 - 13 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	59.2 ms	0 - 13 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X2 Elite	46.163 ms	1 - 1 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X Elite	109.701 ms	841 - 841 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	76.781 ms	0 - 14 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	102.541 ms	0 - 4 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	108.407 ms	0 - 898 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	102.823 ms	0 - 4 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	109.701 ms	841 - 841 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	2061.611 ms	1 - 11 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	161.039 ms	0 - 11 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	59.2 ms	0 - 13 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	161.039 ms	0 - 11 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	44.093 ms	0 - 10 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	57.844 ms	0 - 9 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X2 Elite	46.324 ms	0 - 0 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X Elite	110.043 ms	1 - 1 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 3 Mobile	75.831 ms	1 - 8 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-8275	101.631 ms	0 - 3 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	107.877 ms	0 - 3 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	102.069 ms	0 - 2 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-X7181	110.043 ms	1 - 1 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-6690	1947.206 ms	0 - 7 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-7790	162.759 ms	2 - 10 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-8750	57.844 ms	0 - 9 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 7 Gen 4 Mobile	162.759 ms	2 - 10 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	78.977 ms	3 - 11 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	125.514 ms	4 - 11 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X2 Elite	90.316 ms	4 - 4 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X Elite	217.102 ms	58 - 58 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	152.683 ms	3 - 10 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	210.731 ms	3 - 7 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	222.128 ms	0 - 66 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	189.356 ms	3 - 6 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	217.102 ms	58 - 58 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	5704.912 ms	1 - 8 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	382.051 ms	5 - 11 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	125.514 ms	4 - 11 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	382.051 ms	5 - 11 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	79.079 ms	0 - 8 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	125.339 ms	0 - 8 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X2 Elite	90.166 ms	0 - 0 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X Elite	216.107 ms	0 - 0 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 3 Mobile	151.828 ms	1 - 7 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-8275	210.469 ms	0 - 4 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	221.912 ms	1 - 3 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	189.297 ms	0 - 4 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-X7181	216.107 ms	0 - 0 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-6690	5719.666 ms	2 - 8 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-7790	380.727 ms	0 - 6 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-8750	125.339 ms	0 - 8 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 7 Gen 4 Mobile	380.727 ms	0 - 6 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