Google has introduced new models, Veo 2 and Imagen 3, for generating video and images, promising higher quality and realism. The new Whisk tool allows for remixing images to create unique outputs. The models are available in Google Labs.
Google has announced new versions of its video and image generation models, Veo 2 and Imagen 3, as well as a new experimental tool, Whisk. Veo 2 creates high-quality videos with improved realism and understanding of cinematography, while Imagen 3 produces clearer and better-composed images with more diverse artistic styles. Whisk allows users to input images that express their ideas about the subject, scene, and style, and then remix them into unique outputs.
The Veo 2 model creates high-quality videos with a better understanding of physics, motion, and expressions. It can process complex requests, including genre, lens type, and cinematic effects. Videos can be generated in up to 4K resolution and several minutes in length. Veo 2 is integrated into the VideoFX tool in Google Labs. Google plans to expand Veo 2 to YouTube Shorts and other products.
Imagen 3 generates clearer and better-composed images with more diverse artistic styles.
Whisk combines Imagen 3 with Gemini for visual understanding and description. It allows users to input images and remix them into unique outputs. Whisk is available in the USA.
It seems everyone is trying to jump on the AI media generation bandwagon. However, the potential of Veo 2 and Imagen 3 is undeniable. Imagine AI-generated movies based on a script, personalized real-time ads, or interactive educational videos that adapt to a student's learning style. Veo 2 could disrupt the film industry by enabling independent creators to produce high-quality videos without high costs. Imagen 3 could change the advertising industry with personalized ads generated in real-time. And Whisk? That's just the beginning. Imagine a platform where designers can collaborate on projects in real-time, remixing their ideas with the help of AI. This could lead to an explosion of creativity and entirely new design trends.
Google Labs has unveiled Mixboard, a new AI-powered concepting board designed to challenge Pinterest and Canva. Currently in beta in the U.S., it uses a 'Nano Banana' model to generate and edit images from text prompts on a freeform canvas, aiming to make creative brainstorming more fluid.
Google's Imagen 4 family of AI image generators is now generally available. The release introduces Imagen 4 Fast, a new model for rapid, low-cost creation at $0.02 per image, alongside the high-quality Imagen 4 and detail-focused Imagen 4 Ultra, which both now support 2K resolution.
Google has launched Opal, an experimental no-code tool that allows anyone to build and share simple AI applications using natural language and a visual editor. Currently in a US-only beta, Opal enables users to chain prompts and models to create custom tools for productivity and prototyping.
Google DeepMind's new AI, AlphaGenome, aims to decode the 98% of human DNA that regulates genes. This powerful tool offers new possibilities for understanding diseases like cancer and for advancements in synthetic biology.
