Snap introduced the AI model of the text on a picture for mobile devices that will be powered by some Snapchat features in the coming months. On Tuesday, the company said the model could produce high resolution images for about 1.4 seconds on the iPhone 16 Pro Max.
The new diffusion model is completely triggered on the device, which reduces computer costs compared to models that rely on large servers. Snap notes that the model can create “stunning” visual results “by transferring rich displays from large diffusion models to this smaller and more efficient model.”
Snap plans to introduce technology in the coming months to help the AI -AI Snaps, AI bitmoji origin and more.
The company says that the application of this internal technology will be able to offer its community of high quality AI tools at lower operational costs.
“Snap has a long history of research excellence in the optimization and efficiency of the model,” the blog post states. “We are inspired by an industrial innovation that makes AI tools more effective, more affordable and accessible and look forward to that we will continue to contribute to a fast pace of innovation, especially for experience with first mobile devices.”
The company did not share further details about the model, but she noted that it was a continuation of long -term investment in AI and ML technology.
While Snap was eavesdropping on a tools from companies like Open and Google In the past in order to power some of his features, he has now made his own internal Ai model debut that will allow him to offer his users unique features. It makes sense for the company to invest in AI and develop its own model, especially since almost every technological company, including Meta, has been doing it in recent years.
Snap should publish your Q4 2024 earning report on Tuesday.