How Meta animates AI-generated images at scale

How Meta animates AI-generated images at scale

摘要

We launched Meta AI with the goal of giving people new ways to be more productive and unlock their creativity with generative AI (GenAI). But GenAI also comes with challenges of scale. As we deploy new GenAI technologies at Meta, we also focus on delivering these services to people as quickly and efficiently as possible.

Meta AI’s animate feature, which lets people generate a short animation of a generated image, carried unique challenges in this regard. To deploy and run at scale, our model to generate image animations had to be able to serve billions of people who use our products and services, do so quickly – with fast generation times and minimal errors, and remain resource efficient.

Here’s how we were able to deploy Meta AI’s animate feature using a combination of latency optimizations, traffic management, and other novel techniques.