Skip to main content

A first look at Adobe’s new AI video generation tools

Adobe Creative Cloud Suite apps list
Adobe

Adobe previewed its upcoming video AI tools, part of the Firefly video model the company announced in April, in a newly released YouTube post. The features (and model) are expected to arrive by the end of the year and be available on both the Premiere Pro beta app, as well as on a free website.

Adobe Firefly Video Model Coming Soon | Adobe Video

The company highlighted three new features that are currently in private beta but will be ready for public release later this year: Generative Extend, Text to Video, and Image to Video. Generative Extend will lengthen any input video by up to two seconds, while the Text and Image to Video functions allow users to generate high-definition, five-second-long clips using word and picture prompts.

Recommended Videos

You can then edit and modify those videos, adjusting camera controls to change the camera angles, their motion, and the shooting distance. And unlike Grok, Firefly’s guardrails will block the generation of content that includes nudity, drugs, and alcohol.

Generative Extend will arrive later this year as part of Premiere Pro beta, while Text and Image to Video will be available on Firefly’s website. The latter two should be available to free tier users, though likely with usage limits. The company reportedly plans to eventually integrate the video generation features into the rest of its Creative Cloud, Experience Cloud, and Adobe Express applications.

Adobe bills Firefly’s image and video generations as “commercially safe,” the model having been trained exclusively on licensed, public domain, and Adobe Stock content.

From the teaser video above, Firefly’s upcoming video capabilities appear equivalent to OpenAI’s Sora (itself still unreleased), Kuaishou Technology’s Kling, and Runay’s Gen-3 Alpha model. It certainly looks significantly better, and far less hallucinatory, than what the bevy of free video generators currently available on the internet can produce.

Midjourney is also reportedly working on a text-to-video model. CEO and Founder David Holz, in an “Office HourDiscord session in December 2023, announced that the model would be released in “a few months,” though no updates have been released since then.

Andrew Tarantola
Andrew Tarantola is a journalist with more than a decade reporting on emerging technologies ranging from robotics and machine…
Google will begin labeling AI-generated images in Search
Google Search on mobile

AI-generated images have become increasingly predominant in the results of Google searches in recent months, crowding out legitimate results and making it harder for users to find what they're actually looking for. In response, Google announced on Tuesday that it will begin labeling AI-generated and AI-edited image search results in the coming months.

The company will flag such content through the “About this image” window and it will be applied to Search, Google Lens, and Android's Circle to Search features. Google is also applying the technology to its ad services and is considering adding a similar flag to YouTube videos, but will "have more updates on that later in the year," per the announcement post.

Read more
A new definition of ‘open source’ could spell trouble for Big AI
Meta AI can generate images within a chat in about five seconds.

The Open Source Initiative (OSI), self-proclaimed steward of the open source definition, the most widely used standard for open-source software, announced an update to what constitutes an "open source AI" on Thursday. The new wording could now exclude models from industry heavyweights like Meta and Google.

"Open Source has demonstrated that massive benefits accrue to everyone after removing the barriers to learning, using, sharing, and improving software systems," the OSI wrote in a recent blog post. "For AI, society needs the same essential freedoms of Open Source to enable AI developers, deployers, and end users to enjoy those same benefits."

Read more
People are making entire short films with this new AI video-generation app
screenshot of a MiniMax AI video of a dog running through a field

Alibaba- and Tencent-backed startup Minimax, one of China's "AI tigers," has released its Video-01 text-to-video model, which can generate highly accurate depictions of humans, down to their hand motions. Minimax unveiled the new tool Saturday at its inaugural developer conference in Shanghai.

https://x.com/JunieLauX/status/1829950412340019261

Read more