Intel has released the first release of its AI Playground suite of applications designed to improve artificial intelligence performance, previously demonstrated at Computex 2024. AI Playground is a set of generative AI and chatbot applications that use Intel Arc graphics cards with a minimum of 8 GB of video memory. All applications in the suite are built for the OpenVINO framework and the XMX cores of Arc A-series discrete graphics adapters. As of now, only three models of GPUs from this line have 8 GB of video memory or more – these are the A770, A750, and A580, as well as their mobile variants. The company is working on a version of the program that will be able to run on Intel Core Ultra-H series processors, which use a combination of NPU and iGPU for acceleration. AI Playground is open source. Intel has made an effort to make the package as convenient as possible for customers, providing it with an installer that creates all the necessary software dependencies.
The Intel AI Playground tools include an AI that generates images and can convert cues into standard or HD images. It relies on Stable Diffusion technology, which is supported by the DreamShaper 8 and Juggernaut XL models. It also supports Phi3, LCM LoRA, and LCM LoRA SDXL. All of these have been optimized for Intel Arc GPUs with the “Alchemist” architecture. There is also an AI utility for image enhancement, which can be used for upscaling, detail reconstruction, stylization, inpainting, and coloring, as well as certain types of image manipulation. The third important tool is an AI text chatbot with all the popular LLMs (large language models).
You can download the Intel AI Playground software here link.
Source:
Techpowerup
