Skip to main content

Generative-AI-powered video editing is coming to Instagram

Instagram on iPhone against a colorful background.
Bryan M. Wolfe / Digital Trends

Editing your Instagram videos will soon be as simple as typing out a text prompt, thanks to a new generative AI tool the company hopes to release in 2025, CEO Adam Mosseri announced Thursday.

The upcoming tool, which leverages Meta’s Movie Gen model, will enable users to “change nearly any aspect of your videos,” Mosseri said during his preview demonstration. Those changes range from subtle modifications, like adding a gold chain to his existing outfit or a hippo in the background, to wholesale alterations including swapping his wardrobe or giving himself a felt, Muppet-like appearance.

Recommended Videos

Meta debuted Movie Gen in October to compete with the likes of Runway’s Gen 3 Alpha and OpenAI’s Sora. Designed to “produce custom videos and sounds, edit existing videos, and transform your personal image into a unique video,” Movie Gen incorporates many of the company’s earlier multimodal efforts with Make-A-Scene and Llama to provide users more control over what it outputs. “These models can reason about object motion, subject-object interactions, and camera motion, and they can learn plausible motions for a wide variety of concepts,” Meta wrote in October, “making them state-of-the-art models in their category.”

The demonstration video certainly appears impressive, displaying minimal distortion to Mosseri’s digitized outfits as he gestured and spoke, though none of the effects were on screen for more than a moment. OpenAI’s Sora promised similarly spectacular results when it was first announced in February but has since failed to live up to expectations with its official release. Whether the performance Movie Gen showed off Thursday translates to what users will actually receive next year remains to be seen.

As the multimodal capabilities of large language models have steadily matured, we’ve seen text-to-video AIs rapidly proliferate over the past year. Movie Gen will likely face significant competition in 2025 as more of these tools come to market, though its ability to generate both video and audio from a user’s prompts, as well as edit and personalize clips, are sure to work in its favor.

Andrew Tarantola
Andrew Tarantola is a journalist with more than a decade reporting on emerging technologies ranging from robotics and machine…
​​OpenAI spills tea on Musk as Meta seeks block on for-profit dreams
A digital image of Elon Musk in front of a stylized background with the Twitter logo repeating.

OpenAI has been on a “Shipmas” product launch spree, launching its highly-awaited Sora video generator and onboarding millions of Apple ecosystem members with the Siri-ChatGPT integration. The company has also expanded its subscription portfolio as it races toward a for-profit status, which is reportedly a hot topic of debate internally.

Not everyone is happy with the AI behemoth abandoning its nonprofit roots, including one of its founding fathers and now rival, Elon Musk. The xAI chief filed a lawsuit against OpenAI earlier this year and has also been consistently taking potshots at the company.

Read more
OpenAI’s Advanced Voice Mode can now see your screen and analyze videos
Advanced Santa voice mode

OpenAI's "12 Days of OpenAI" continued apace on Wednesday with the development team announcing a new seasonal voice for ChatGPT's Advanced Voice Mode (AVM), as well as new video and screen-sharing capabilities for the conversational AI feature.

Santa Mode, as OpenAI is calling it, is a seasonal feature for AVM, and offers St. Nick's dulcet tones as a preset voice option. It is being released to Plus and Pro subscribers through the website and mobile and desktop apps starting today and will remain so until early January. To access the limited-time feature, first sign in to your Plus or Pro account, then click on the snowflake icon next to the text prompt window.

Read more
OpenAI’s Sora doesn’t feel like the game-changer it was supposed to be
Sora's interpretation of gymnastics

OpenAI has teased, and repeatedly delayed, the release of Sora for nearly a year. On Tuesday, the company finally unveiled a fully functional version of the new video-generation model destined for public use and, despite the initial buzz, more and more early users of the release don't seem overly impressed. And neither am I.

https://x.com/OpenAI/status/1758192957386342435

Read more