library_name: pytorch
license: other
tags:
- generative_ai
- android
pipeline_tag: unconditional-image-generation
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 1.25.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.45, ONNX Runtime 1.25.0 | 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 | Snapdragon® 8 Elite Mobile | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | 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 |
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 | 3.901 ms | 1 - 1 MB | NPU |
| text_encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 7.58 ms | 418 - 418 MB | NPU |
| text_encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.73 ms | 0 - 12 MB | NPU |
| text_encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 8.119 ms | 0 - 450 MB | NPU |
| text_encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 8.084 ms | 0 - 3 MB | NPU |
| text_encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 12.156 ms | 0 - 6 MB | NPU |
| text_encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 4.902 ms | 0 - 13 MB | NPU |
| text_encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 68.933 ms | 1 - 10 MB | NPU |
| text_encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 4.941 ms | 0 - 7 MB | NPU |
| text_encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 12.156 ms | 0 - 6 MB | NPU |
| text_encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 4.941 ms | 0 - 7 MB | NPU |
| text_encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 7.58 ms | 418 - 418 MB | NPU |
| text_encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 4.245 ms | 0 - 0 MB | NPU |
| text_encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 7.848 ms | 0 - 0 MB | NPU |
| text_encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.754 ms | 0 - 7 MB | NPU |
| text_encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8275 | 17.392 ms | 0 - 8 MB | NPU |
| text_encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 8.057 ms | 0 - 1 MB | NPU |
| text_encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | 8.365 ms | 0 - 8 MB | NPU |
| text_encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8650P | 8.365 ms | 0 - 8 MB | NPU |
| text_encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8255P | 8.365 ms | 0 - 8 MB | NPU |
| text_encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 8.072 ms | 0 - 2 MB | NPU |
| text_encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 12.127 ms | 0 - 7 MB | NPU |
| text_encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 4.833 ms | 0 - 9 MB | NPU |
| text_encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 72.714 ms | 0 - 7 MB | NPU |
| text_encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | 17.392 ms | 0 - 8 MB | NPU |
| text_encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Mobile | 4.936 ms | 0 - 13 MB | NPU |
| text_encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 12.127 ms | 0 - 7 MB | NPU |
| text_encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 4.936 ms | 0 - 13 MB | NPU |
| text_encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 7.848 ms | 0 - 0 MB | NPU |
| unet | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 67.778 ms | 1 - 1 MB | NPU |
| unet | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 157.367 ms | 842 - 842 MB | NPU |
| unet | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 110.437 ms | 1 - 12 MB | NPU |
| unet | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 153.045 ms | 0 - 898 MB | NPU |
| unet | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 147.603 ms | 0 - 3 MB | NPU |
| unet | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 214.099 ms | 1 - 11 MB | NPU |
| unet | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 72.214 ms | 0 - 12 MB | NPU |
| unet | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 2379.404 ms | 1 - 11 MB | NPU |
| unet | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 101.93 ms | 0 - 12 MB | NPU |
| unet | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 214.099 ms | 1 - 11 MB | NPU |
| unet | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 101.93 ms | 0 - 12 MB | NPU |
| unet | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 157.367 ms | 842 - 842 MB | NPU |
| unet | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 67.582 ms | 0 - 0 MB | NPU |
| unet | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 157.514 ms | 0 - 0 MB | NPU |
| unet | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 110.473 ms | 0 - 7 MB | NPU |
| unet | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8275 | 345.877 ms | 0 - 8 MB | NPU |
| unet | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 153.218 ms | 1 - 2 MB | NPU |
| unet | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | 147.911 ms | 0 - 8 MB | NPU |
| unet | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8650P | 147.911 ms | 0 - 8 MB | NPU |
| unet | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8255P | 147.911 ms | 0 - 8 MB | NPU |
| unet | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 146.958 ms | 0 - 2 MB | NPU |
| unet | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 213.045 ms | 0 - 7 MB | NPU |
| unet | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 66.182 ms | 0 - 8 MB | NPU |
| unet | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 2407.314 ms | 1 - 12 MB | NPU |
| unet | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | 345.877 ms | 0 - 8 MB | NPU |
| unet | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Mobile | 100.205 ms | 1 - 14 MB | NPU |
| unet | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 213.045 ms | 0 - 7 MB | NPU |
| unet | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 100.205 ms | 1 - 14 MB | NPU |
| unet | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 157.514 ms | 0 - 0 MB | NPU |
| vae | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 129.09 ms | 4 - 4 MB | NPU |
| vae | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 257.967 ms | 66 - 66 MB | NPU |
| vae | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 197.375 ms | 3 - 11 MB | NPU |
| vae | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 261.9 ms | 3 - 6 MB | NPU |
| vae | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 242.147 ms | 3 - 6 MB | NPU |
| vae | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 503.769 ms | 2 - 8 MB | NPU |
| vae | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 122.119 ms | 3 - 12 MB | NPU |
| vae | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 6258.16 ms | 2 - 9 MB | NPU |
| vae | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 161.211 ms | 4 - 10 MB | NPU |
| vae | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 503.769 ms | 2 - 8 MB | NPU |
| vae | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 161.211 ms | 4 - 10 MB | NPU |
| vae | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 257.967 ms | 66 - 66 MB | NPU |
| vae | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 128.657 ms | 0 - 0 MB | NPU |
| vae | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 258.203 ms | 0 - 0 MB | NPU |
| vae | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 196.294 ms | 0 - 7 MB | NPU |
| vae | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8275 | 713.424 ms | 0 - 8 MB | NPU |
| vae | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 258.832 ms | 1 - 2 MB | NPU |
| vae | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | 244.729 ms | 0 - 9 MB | NPU |
| vae | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8650P | 244.729 ms | 0 - 9 MB | NPU |
| vae | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8255P | 244.729 ms | 0 - 9 MB | NPU |
| vae | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 242.132 ms | 0 - 3 MB | NPU |
| vae | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 502.136 ms | 0 - 6 MB | NPU |
| vae | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 120.49 ms | 0 - 9 MB | NPU |
| vae | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 6299.823 ms | 23 - 29 MB | NPU |
| vae | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | 713.424 ms | 0 - 8 MB | NPU |
| vae | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Mobile | 160.335 ms | 0 - 14 MB | NPU |
| vae | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 502.136 ms | 0 - 6 MB | NPU |
| vae | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 160.335 ms | 0 - 14 MB | NPU |
| vae | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 258.203 ms | 0 - 0 MB | NPU |
License
- The license for the original implementation of Stable-Diffusion-v2.1 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
