Google Imagen 2 AI model gains video generation capabilities

Google has upgraded its native artificial intelligence (AI)-driven image generation model Imagen 2, adding two new features. The capabilities were announced at the annual Cloud Next conference in Las Vegas. The AI ​​tool is an enterprise-focused product available in the Vertex AI developer platform that helps companies create logo elements and other visual assets. Now, the tech giant has also added a video generation feature to the AI ​​model, which can generate videos up to four seconds long.

The company calls the video generation feature “text to live images.” With this feature, Imagen 2 can create four-second videos based on text prompts. The videos will feature a range of camera angles and movements.according to a Report Provided by VentureBeat, the resulting video is 24 frames per second and has a resolution of 360×640 pixels. Google reportedly plans to improve these metrics in the future.

Google also posted a video on YouTube demonstrating the capabilities of its AI model. Google Cloud CEO Thomas Kurian reportedly said in a press release that animated images can increase user engagement. Build quality appears to be similar to Runway AI and Pika 1.0 – both available for public and corporate use.

There is also the issue of deepfakes. This is relevant because Gemini AI has recently been criticized for showing “inaccuracies in some historical image generation descriptions.” Shortly after, Google removed Gemini’s image generation functionality. But things will be different at Imagen, the company said.company spokesperson Tell TechCrunch, “The Imagen 2 models in Vertex AI are not experiencing the same issues as the Gemini app. We continue to conduct extensive testing and engage with customers.” As for additional protection, images and videos generated by the AI ​​models will be processed through Google Tags using DeepMind’s SynthID technology.

In addition to video generation, Imagen 2 also has repair and restoration features. This will allow users to edit specific parts of an image rather than regenerating the entire image with new prompts. Making subtle changes to your images is an easier way to get the results you want. Microsoft’s Copilot and OpenAI’s DALL-E 3 also provide this functionality.