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® 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-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® X2 Elite	3.754 ms	1 - 1 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X Elite	7.592 ms	418 - 418 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	5.863 ms	0 - 12 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	7.879 ms	0 - 4 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	8.139 ms	0 - 450 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	8.103 ms	0 - 3 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	7.592 ms	418 - 418 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	68.778 ms	1 - 12 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	12.131 ms	1 - 9 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	4.941 ms	0 - 12 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Mobile	4.941 ms	0 - 12 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	4.841 ms	0 - 11 MB	NPU
text_encoder	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	12.131 ms	1 - 9 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X2 Elite	4.268 ms	0 - 0 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X Elite	7.864 ms	0 - 0 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 3 Mobile	5.772 ms	0 - 7 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-8275	7.848 ms	0 - 3 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	8.078 ms	0 - 2 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8775P	8.368 ms	0 - 9 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8650P	8.368 ms	0 - 9 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8255P	8.368 ms	0 - 9 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-9075	8.081 ms	2 - 4 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-X7181	7.864 ms	0 - 0 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-6690	68.646 ms	0 - 6 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-7790	12.004 ms	0 - 6 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-8750	4.928 ms	0 - 13 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA7255P	17.393 ms	0 - 8 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Mobile	4.928 ms	0 - 13 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	4.839 ms	0 - 9 MB	NPU
text_encoder	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 7 Gen 4 Mobile	12.004 ms	0 - 6 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X2 Elite	67.424 ms	1 - 1 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X Elite	157.327 ms	842 - 842 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	109.974 ms	0 - 10 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	145.783 ms	0 - 4 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	152.934 ms	0 - 898 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	147.343 ms	0 - 3 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	157.327 ms	842 - 842 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	2498.457 ms	1 - 11 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	213.549 ms	1 - 11 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	100.758 ms	0 - 11 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Mobile	100.758 ms	0 - 11 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	76.231 ms	0 - 12 MB	NPU
unet	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	213.549 ms	1 - 11 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X2 Elite	67.744 ms	0 - 0 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X Elite	157.565 ms	0 - 0 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 3 Mobile	109.065 ms	0 - 7 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-8275	145.297 ms	0 - 3 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	152.631 ms	0 - 2 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8775P	147.773 ms	0 - 9 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8650P	147.773 ms	0 - 9 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8255P	147.773 ms	0 - 9 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-9075	146.465 ms	0 - 2 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-X7181	157.565 ms	0 - 0 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-6690	2312.991 ms	0 - 6 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-7790	213.47 ms	0 - 7 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-8750	98.723 ms	1 - 13 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA7255P	345.88 ms	0 - 10 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Mobile	98.723 ms	1 - 13 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	65.752 ms	0 - 10 MB	NPU
unet	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 7 Gen 4 Mobile	213.47 ms	0 - 7 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X2 Elite	128.588 ms	4 - 4 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X Elite	257.442 ms	65 - 65 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	195.543 ms	3 - 11 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	262.394 ms	3 - 7 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	263.585 ms	4 - 5 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	241.413 ms	3 - 6 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	257.442 ms	65 - 65 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	6319.462 ms	1 - 8 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	503.986 ms	2 - 8 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	159.012 ms	4 - 16 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Mobile	159.012 ms	4 - 16 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	123.122 ms	4 - 12 MB	NPU
vae	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	503.986 ms	2 - 8 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X2 Elite	129.083 ms	0 - 0 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X Elite	257.599 ms	0 - 0 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 3 Mobile	196.884 ms	3 - 10 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-8275	262.667 ms	0 - 4 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	261.506 ms	1 - 2 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8775P	244.78 ms	0 - 9 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8650P	244.78 ms	0 - 9 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8255P	244.78 ms	0 - 9 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-9075	241.351 ms	2 - 5 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ IQ-X7181	257.599 ms	0 - 0 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-6690	6336.612 ms	2 - 8 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-7790	503.612 ms	0 - 6 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® Dragonwing™ Q-8750	159.831 ms	0 - 9 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA7255P	713.323 ms	0 - 10 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Mobile	159.831 ms	0 - 9 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	120.649 ms	0 - 10 MB	NPU
vae	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 7 Gen 4 Mobile	503.612 ms	0 - 6 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