When you buy from our articles through links, Future and its syndication partners may earn a commission.
Google is testing an update to Veo, a generative AI video platform, that would give the software the ability to replicate specific lenses and cinematic effects. In a blog post this week, Google shared a look at the rollout of Veo 2 to Google Labs, alongside an updated Imagen 3 generative imaging platform and an experimental program called Whisk that uses AI to combine elements from multiple images.
This week’s announcements are already rolling out to some users through Google Labs, the company’s platform for testing experimental software. Veo 2’s generative AI model can be tested in VideoFx on Labs, while Imagen 3’s testing is being rolled out to ImageFX and Whisk is a standalone experiment.
Veo 2 video generator understands industry jargon
In a blog post, Google says Veo 2 “understands the unique language of cinematography.” For example, the company explained that users could request an “18mm lens” and the software would deliver a wide-angle view. Google notes that the program can also understand terms like “shallow depth of field,” as well as instructions for camera movement and framing.
Google says Veo 2 also improves its understanding of real-world physics – which, as a virally generated gymnastics video recently showed, is a key challenge for generative AI. The company says the software also better understands human movements and expressions and reduces unnecessary details such as extra fingers.
Like the original Veo, AI-generated videos will be embedded with SynthID, a kind of invisible watermark that marks the file as AI-generated. Although the SynthID tag is not visible on the video itself, other software can mark the video as AI-generated.
The beta software can generate images up to 4K and “minutes” long, Google says. Both specifications are remarkable, since competitor OpenAI Sora is limited to FullHD videos of a maximum of 20 seconds.
The updated AI generator is rolling out to early beta testers via Google Labs and VideoFX. But Google expects the generative AI software to roll out to YouTube Shorts and other products as early as next year.
Google’s Whisk uses AI to create images from reference images
Google also announced Whisk, an experimental AI that allows users to upload multiple images to generate a remix. Users upload a photo of the subject, scene and style, and write text prompts, then the software creates something new based on the reference photos and text.
The ability to merge multiple images to create a new file could raise copyright concerns among visual artists, building on existing concerns about generative AI among creatives.
Google says the experimental software combines Imagen 3 and Gemini to understand what’s in the images and text. As experimental software, it will first launch in Google Labs and will initially only be available for testing in the US.
Google’s Imagen 3 image generator becomes more realistic
Google’s generative still image AI also saw newly announced features this week. According to Google, Imagen 3 produces images with better composition than its predecessor and also generates more styles.
That style list includes photorealism and, Google notes, the AI is capable of generating more realistic details and textures. Textures have traditionally been a challenge for AI systems; lack of texture is often one of the signs that an image is generated rather than photographed. Google also says the updated software has better and faster understanding.
Imagen 3 is being rolled out to testers via Google Labs.
You might like it too
To learn more about generative AI, read our list of the best AI image generators, our guide to AI image software, or learn how to tell if an image was generated by AI.