Google has introduced Veo 2, an upgraded version of its generative AI video tool, to early testers. This new model boasts improved understanding of cinematography and real-world physics, addressing common challenges in generative video models. Notably, Veo 2 aims to reduce artifacts like extra fingers, which have plagued previous iterations.
In addition to Veo 2, Google is enhancing its Imagen 3 text-to-image model, which now generates brighter images and adheres more closely to prompts. The rollout of these updates is part of Google's strategy to refine its AI offerings, with Veo 2 available to Google Labs users in the US. Comparatively, other models like Sora offer longer video generation capabilities, highlighting the competitive landscape in AI video generation.
• Veo 2 improves understanding of cinematography and physics in video generation.
• Imagen 3 enhances image quality and prompt adherence for better outputs.
Generative AI refers to algorithms that can create new content, such as videos or images, based on learned patterns.
Cinematography involves the art and technology of motion picture photography, which Veo 2 aims to understand better.
Prompt adherence is the ability of an AI model to follow user instructions accurately when generating content.
Google is a leading technology company that develops AI tools like Veo and Imagen for various applications.
Isomorphic Labs, the AI drug discovery platform that was spun out of Google's DeepMind in 2021, has raised external capital for the first time. The $600
How to level up your teaching with AI. Discover how to use clones and GPTs in your classroom—personalized AI teaching is the future.
Trump's Third Term? AI already knows how this can be done. A study shows how OpenAI, Grok, DeepSeek & Google outline ways to dismantle U.S. democracy.
Sam Altman today revealed that OpenAI will release an open weight artificial intelligence model in the coming months. "We are excited to release a powerful new open-weight language model with reasoning in the coming months," Altman wrote on X.