SNAP has announced a research model from AI text to images for mobile devices that will enhance some of Snapchat’s capabilities in the coming months. The company said Tuesday that the model can generate high-resolution images on the iPhone 16 Pro Max in about 1.4 seconds.
The new spreading model runs fully on the device and reduces computational costs compared to models that rely on large servers. SNAP points out that models can produce “stellar” visual results by “transferring rich representations to large and efficient models.”
SNAP plans to produce technology in the coming months to enhance the AI snaps of apps, AI Bitmoji background and more.
The company says that implementing the in-house technology will allow the community to deliver high-quality AI tools at lower operating costs.
“SNAP has a long history of research excellence in model optimization and efficiency,” the company said in a blog post. “We are inspired by industry innovations that make AI tools more efficient, affordable and accessible, and look forward to continuing to contribute to the rapid pace of innovation, especially for mobile-first experiences. It’s there.”
The company did not share details about the model, but noted that it is a continuation of long-term investments in AI and ML technologies.
SNAP has tapped AI tools from companies such as Openai and Google to enhance some of its features, but has debuted its own in-house AI model that can provide unique features to its users. It makes sense for the company to invest in AI and develop its own models, especially as almost all high-tech companies, including META, have done so over the past few years.
SNAP is scheduled to release its fourth quarter 2024 revenue report on Tuesday.
TechCrunch has a newsletter focused on AI! Sign up here to get it every Wednesday in your inbox.