Vidu 2.0 sets new benchmarks for speed and affordability in video AI

· 2 min read
Vidu

ShengShu Technology has announced the release of Vidu 2.0, an updated version of its flagship generative video platform, which the company claims is the fastest and most cost-effective solution in the industry. With a user base of over 10 million within just 100 days of its initial launch, Vidu 2.0 introduces groundbreaking features that significantly enhance video generation speed, reduce costs, and simplify the creative process.

The key feature of Vidu 2.0 is its ability to generate high-resolution video clips in under ten seconds, a marked improvement over traditional generative video tools that typically require tens of minutes or hours. This advancement is powered by ShengShu’s proprietary full-stack interference accelerator, based on its U-ViT research framework. The platform maintains high-quality output while delivering these unprecedented speeds, making it ideal for creators, editors, and brands seeking rapid content production for tasks like A/B testing.

Additionally, Vidu 2.0 offers substantial cost savings. The platform’s per-second video generation cost has been reduced to $0.0375—55% lower than the industry average and 50% cheaper than its predecessor, Vidu 1.5. This affordability makes advanced video generation accessible to small businesses and independent creators who previously faced financial barriers.

Another standout feature is the introduction of “Templates,” a library of pre-set prompts designed to simplify the creative process. These templates allow users to add complex actions or props to their videos with a single click, eliminating the need for detailed technical knowledge in prompt engineering. ShengShu plans to continuously expand this library to accommodate a wider range of use cases.

According to Jiayu Tang, CEO and co-founder of ShengShu Technology, Vidu 2.0 represents a significant step toward real-time co-creation in generative content. The platform’s multimodal capabilities not only enhance user creativity but also pave the way for interactive storytelling experiences where users can dynamically shape narratives through their choices.

Since its initial launch in July 2024, Vidu has been at the forefront of generative video innovation. Earlier updates, such as Vidu 1.5’s Multiple-Entity Consistency feature, demonstrated ShengShu’s commitment to blending diverse elements into cohesive visual outputs. With Vidu 2.0, ShengShu continues to push boundaries, aiming for mass adoption of generative video technologies.

Founded in March 2023 and headquartered in Singapore, ShengShu Technology specializes in advanced diffusion models and transformer-based architectures for multimodal content generation. The company’s mission is to integrate text, images, videos, and 3D content into seamless creative workflows that empower users across industries like art design, gaming, filmmaking, and social media.

💡
Try Vidu 2.0 over here

Vidu 2.0 is expected to set new standards for speed, affordability, and accessibility in generative video production while laying the groundwork for future innovations in AI-driven storytelling and real-time content creation.