AI-generated content is getting pretty big lately. Not long ago, OpenAI released Sora, a text-to-video model designed to create short, high-quality clips, bringing words to life in a way that feels almost too real. The catch is that it’s capped at 20 seconds and delivers HD content (1080p).
Fast forward to today, and Google's DeepMind is not backing down. If anything, they’re stepping up the competition with the launch of Veo 2, the successor to Veo 1. According to DeepMind, Veo 2 can create full-on, 4K videos that can run up to 2 minutes long. If you want to give it a go, you’ll need to check it out on VideoFX, but there’s a bit of a waitlist at the moment. DeepMind says they’re expanding access, though, so it could be coming your way sooner rather than later.
One example shared on their website is a video created from a prompt that’s as detailed as it gets. The prompt describes a slow dolly shot of a Renaissance palace, complete with velvet drapes, gold-inlaid furniture, chandeliers casting soft light, and a stoic queen sitting at a desk. There’s a letter on the desk, courtiers murmuring in the background, and every single detail in the room feels heavy with the weight of betrayal:
Here’s the actual prompt used in the example:
The camera moves in a slow dolly shot, revealing the opulence of a Renaissance palace chamber adorned with gold-inlaid furniture, velvet drapes, and chandeliers casting soft, flickering light. A queen sits motionless at a gilded desk, her crimson silk gown cascading onto the floor like spilled blood. On the desk lies an unsigned letter, its edges curled with age. The camera frames her from behind, catching the reflection of her stoic face in a massive, ornate mirror. In the background, courtiers murmur, their silhouettes dancing like ghosts in the candlelight. The room feels heavy, every gilded detail amplifying an air of betrayal and paranoia. The color palette alternates between deep, regal reds and cold golds, with chiaroscuro lighting intensifying the drama. Shot on 70mm film for rich texture, evoking the grandeur of historical masterpieces.
Now, let’s not get too carried away. While these examples are stunning, it’s worth mentioning that DeepMind has probably handpicked these to show off the best of what Veo 2 can do. It’s not all perfect. One of the limitations they’ve pointed out is that generating complex scenes or motion can still be a challenge for the model.
0 Comments - Add comment