deneme bonusu
Qualcomm ran a complete Stable Diffusion AI model on an Android phone | Insider Feeds %

Qualcomm ran a complete Stable Diffusion AI model on an Android phone




Forward-looking: Stable Diffusion is a deep learning model capable of turning words into eerie, distinctly artificial images. The machine learning network usually runs in the cloud and it can also be installed on a beefy PC to work offline. With further optimizations, the model can be efficiently run on Android smartphones as well.

Qualcomm was able to adapt the image creation capabilities of Stable Diffusion to a single Android smartphone powered by a Snapdragon 8 Gen 2 SoC device. It is a remarkable result which, according to the San Diego-based company, is just the beginning for AI applications managed on edge computing devices. No internet connection is required, Qualcomm assures.

As explained on Qualcomm’s corporate blog, Stable Diffusion is a large foundation model employing a neural network trained on a vast quantity of data at scale. The text-to-image generative AI contains one billion parameters, and it has mostly been “confined” in the cloud (or on a traditional x86 computer equipped with a recent GPU).

Qualcomm AI Research employed “full-stack AI optimizations” to deploy Stable Diffusion on an Android smartphone for the very first time, at least with the kind of performance described by the company. Full-stack AI means that Qualcomm had to tailor the application, the neural network model, the algorithms, the software and even the hardware, even though some compromises were clearly required to get the job done.

First and foremost, Qualcomm had to shrink the Single-precision floating-point data format (or FP32) used by Stable Diffusion to the lower-precision INT8 data type. By using its newly-created AI Model Efficiency Toolkit’s (AIMET) post-training quantization, the company was able to greatly increase performance while also saving power and maintaining model accuracy at this lower precision with no need for costly re-training.

The result of this full-stack optimization was the ability to run Stable Diffusion on a phone, generating a 512 x 512 pixel image in under 15 seconds for 20 inference steps. This is the fastest inference on a smartphone and “comparable to cloud latency,” Qualcomm stated, while user input for the textual prompt remains “completely unconstrained.”

Running Stable Diffusion on a phone is just the beginning, Qualcomm said, as the ability to run large AI models on edge devices provides many benefits such as reliability, latency, privacy, efficiency, and cost. Furthermore, full-stack optimizations for AI-based hardware accelerators can easily be used for other platforms such as laptops, XR headsets and “virtually any other device powered by Qualcomm Technologies.”


Source link

Subscribe to our magazine

━ more like this

Understanding and Excelling in the HSC Short Syllabus in Bangladesh

Introduction: The Higher Secondary Certificate (HSC) Short Syllabus in Bangladesh has been introduced to overcome academic challenges and ensure effective learning. This comprehensive guide explores...

A Detailed Exploration of SSC Exam Routine 2024 in Bangladesh

Introduction: Embarking on the academic journey, the Secondary School Certificate (SSC) exam holds paramount significance for students in Bangladesh. This comprehensive guide navigates the intricacies...

A Comprehensive Guide to PESP Finance Gov BD

Introduction: In the intricate world of financial management, PESP Finance Gov BD emerges as a key player. This comprehensive guide explores the various aspects of...

Innovative Uses for Coffee Burlap Bags in Your Garden

Demystifying Coffee Burlap Bags Before we dive into their myriad uses, let's acquaint ourselves with coffee burlap bags. Made from robust natural burlap fibers, they're...

Unlocking the Benefits of Online Shopping with Credit Cards: Why OneCard Might Be Your Best Bet?

Indians are increasingly opting for online shopping over in-store purchases, with credit card transactions online outpacing those at physical Point of Sale (PoS) locations...