Google’s AI Video Model Veo 2 Goes Live on Freepik

Google’s AI video generation model Veo 2 is now available for public use on the Freepik platform. Freepik provides AI tools to generate content and a stock image library. Today, it announced it would be the first platform to feature Google’s Veo 2. 

“Google partners with us to debut the most advanced AI video model. Unmatched realism, precision, and smooth animations,” said Freepik in a post on X. 

Google’s Veo 2 will consume 1,000 credits per generation on the Freepik platform. Moreover, Freepik announced that the first 10,000 users can run two Veo 2 generations for free. You can check out the number of credits each Freepik plan offers and its pricing here. 

Moreover, Freepik published a few “hand-picked” prompts and examples of videos generated from Veo 2 by its team of creators. 

Recently, Google announced that Veo 2 was integrated into YouTube Shorts as an upgrade to the Dream Screen feature. This feature allows users to create video clips from text-based prompts. 

Last December, Google announced the Veo 2 model, and the company’s product lead, Logan Kilpatrick, revealed that they will hit API by early next year. 

The model handles complex elements like reflections and shadows, producing clearer and sharper footage. It also includes SynthID watermarking for safety.

Google’s internal testing indicates that Veo outperforms competitors such as China’s Kling, Meta’s Movie Gen, and OpenAI’s Sora in terms of quality and prompt adherence. 

Google’s Veo 2 has been advertised as a tool that brings advanced capabilities in terms of cinematic understanding. “Veo 2 delivers lifelike visuals with enhanced realism, reducing artefacts and improving detail. Its motion simulation accurately replicates simple and complex movements using physics,” said Google DeepMind’s Tom Hume on X. 

The Veo 2 supports 4K resolution and can produce videos longer than two minutes, although its experimental platform currently restricts it to 720p and eight seconds. It outperforms OpenAI’s  Sora with four times the resolution and six times the video duration.