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…
Grok 2.0 takes the guardrails off AI image generation
Elon Musk as Wario in a sketch from Saturday Night Live.

Elon Musk's xAI company has released two updated iterations of its Grok chatbot model, Grok-2 and Grok-2 mini. They promise improved performance over their predecessor, as well as new image-generation capabilities that will enable X (formerly Twitter) users to create AI imagery directly on the social media platform.

“We are excited to release an early preview of Grok-2, a significant step forward from our previous model, Grok-1.5, featuring frontier capabilities in chat, coding, and reasoning. At the same time, we are introducing Grok-2 mini, a small but capable sibling of Grok-2. An early version of Grok-2 has been tested on the LMSYS leaderboard under the name 'sus-column-r,'” xAI wrote in a recent blog post. The new models are currently in beta and reserved for Premium and Premium+ subscribers, though the company plans to make them available through its Enterprise API later in the month.

Read more
Nvidia is taking generative AI into a whole new dimension
A visualization of Nvidia's Omniverse platform.

We've seen plenty of generative AI tools that can spit out images, from Microsoft Designer to Stable Diffusion, but Nvidia is taking generative AI into a new dimension -- literally. The company announced a partnership with Shutterstock at Siggraph 2024 that will allow users to generate 3D models using generative AI.

There are handful of AI tools that can generate 3D models, but Shutterstock's take is definitely the most official tool we've seen so far. The models will live in Shutterstock's TurboSquid library, which currently hosts the company's library of 3D assets. To generate new assets, Shutterstock says users will be able to provide text and images as prompts. From there, designers can take the assets and edit them in separate apps, with exports available "in a variety of popular file formats," according to Nvidia.

Read more
Adobe Illustrator’s vector AI features just got a huge update
A butterfly with vectors filled in using generative AI feature.

Adobe has announced a significant update to Illustrator's generative AI features that designers should appreciate. The headlining new feature is Generative Shape Fill, which add vector to shapes using just text.

Adobe demoed the feature in a briefing to the press, using the prompt "cute 3D robot" to fill in some basic shapes with vector details. The feature even lets you set the shape strength, detail level, color and tone, and style references.

Read more