Google has upgraded its native artificial intelligence (AI)-powered image generation model Imagen 2 with two new capabilities. The capabilities were announced at its annual CloudNext conference in Las Vegas. AI Tool is an enterprise-focused product available within the Vertex AI developer platform and can help companies create logo elements and other visual assets. Now, the tech giant has also added video generation capabilities to the AI ​​model and it can create videos up to four seconds long.

The video generation feature is being called ‘Text to Live Image’ by the company. With this capability, Imagen 2 can create four-second-long videos from text prompts. These videos will have limited camera angles and movement. According to one Reports Via VentureBeat, the produced videos will have 24 frames per second and will be delivered at a resolution of 360×640 pixels. Google reportedly plans to improve these metrics in the future.

Google has also posted a video on YouTube to demonstrate the capabilities of its AI model. Google Cloud CEO Thomas Koren reportedly said in a press release that animations can improve user engagement. Generation Quality looks similar to Runway AI and Pika 1.0 — both available to the general public as well as businesses.

There is also the question of Deep Fax. This is relevant since the Gemini AI recently came under fire after it revealed “errors in the creation of some historical images”. Shortly after, Google removed the image generation feature from Gemini. But the company says that will be different with Imagen. Company spokesperson told TechCrunch, “The Imagen 2 model in Vertex AI has not encountered the same issues as the Gemini app. We continue to test extensively and engage with our customers. As for additional protection, through the AI ​​model The generated images and videos will be labeled with Google DeepMind’s Synth ID technology.

In addition to video generation, Imagen 2 also has painting and outpainting capabilities. This will allow users to recreate the entire image with a new prompt instead of editing a specific part of the image. Making granular changes to an image is an easy way to achieve the desired result. This feature is also offered by Microsoft’s Copilot and OpenAI’s DALL-E 3.