Date: December 17, 2024
Google’s DeepMind claims that 59% of human raters chose Veo 2’s output over Sora Turbo, Minimax, and Meta’s MovieGen AI video generators.
Google’s DeepMind team has brought a new AI video generator tool that surpasses all of its competitors’ top offerings. Google just launched its Veo 2 video generator seven months after releasing the first version. This move comes right after Sora and Sora Turbo video generators were launched after staying in the preview stage for nearly three quarters.
Veo 2 can generate videos with up to 4k resolution, whereas Sora Turbo churns out videos with up to 1080p resolution. According to Google’s claim, Veo 2 can improvise scenes through a newly introduced ‘Camera Control’ feature to generate footage from certain angles and cinematic styles. This feature plays a critical role in providing a competitive edge to Google as there is no actual camera involved. Users only need to prompt the model for specific camera shots and angles, ranging from closeups to broader landscape coverages.
The existing market of AI video generators includes Sora AI, Sora Turbo, Runway, Midjourney, Minimax, and MovieGen. Runway tops all existing AI video generation models, but it is limited to a fuzzy 720p video output. This is where DeepMind’s Veo 2 takes the lead.
DeepMind also claims that during a comparative survey, 59% of human raters chose Google’s AI Veo 2, while only 27% opted for the Sora Turbo AI model. Similar victories are being claimed for comparative tests against Minimax and Meta’s MovieGen. The only comparison where Veo 2 slipped slightly below 50% in preference is with Kling V1.5, a Kuaishou technology product of Chinese origins.
Veo 2’s practical benefits further enhance its position above other AI video generators. Veo 2 can generate 4k resolution clips of 8 seconds by default, but they can be extended to more than two minutes of footage as well. No other AI video generator offers such long-duration content generation options, even in lower resolutions. Sora’s 1080p clips are capped at 20 seconds max.
The efficiency of Veo 2 is a strong indicator of Google’s mission to dominate the AI video generation market globally. Its accuracy of prompt adherence adds another feather to the cap, making it one of the best AI video generators in the market.
By Arpit Dubey
Arpit is a dreamer, wanderer, and tech nerd who loves to jot down tech musings and updates. With a knack for crafting compelling narratives, Arpit has a sharp specialization in everything: from Predictive Analytics to Game Development, along with artificial intelligence (AI), Cloud Computing, IoT, and let’s not forget SaaS, healthcare, and more. Arpit crafts content that’s as strategic as it is compelling. With a Logician's mind, he is always chasing sunrises and tech advancements while secretly preparing for the robot uprising.
OpenAI Is Building an Audio-First AI Model And It Wants to Put It in Your Pocket
New real-time audio model targeted for Q1 2026 alongside consumer device ambitions.
Nvidia in Advanced Talks to Acquire Israel's AI21 Labs for Up to $3 Billion
Deal would mark chipmaker's fourth major Israeli acquisition and signal shifting dynamics in enterprise AI.
Nvidia Finalizes $5 Billion Stake in Intel after FTC approval
The deal marks a significant lifeline for Intel and signals a new era of collaboration between two of America's most powerful chipmakers.
Manus Changed How AI Agents Work. Now It's Coming to 3 Billion Meta Users
The social media giant's purchase of the Singapore-based firm marks its third-largest acquisition ever, as the race for AI dominance intensifies.