SINGAPORE, Jan. 15, 2025 /PRNewswire/ -- ShengShu Technology, a pioneer in generative video, is introducing a game-changing Vidu 2.0 update for its flagship video generation application Vidu. With 10 million users in just 100 days, Vidu and its latest update represents a critical benchmark as the industry's fastest and the most affordable video generation platforms. Vidu 2.0 introduces the ability to generate a clip in under ten seconds, 55% cheaper than the industry's average, and generate complex actions or props with just a single click.
With faster speeds, lower costs, and a user-friendly interface, Vidu 2.0 is the new milestone in ShengShu Technology's ambitious roadmap for generative video. It marks a pivotal moment that introduces a new way to think about content. Vidu 2.0 lays the foundation for a future where next-generation AI-driven storytelling could adapt dynamically to every choice made by the user. Imagine a world where users might roleplay as a film's protagonist, shaping the narrative through clicks, spoken commands, or camera interactions. Whether choosing to fight, flee, or join the antagonist, AI could generate a personalized storyline for every decision, offering an entirely new way to experience storytelling. And, this vision may sooner than later become a reality. Supported by continued reduced barriers to entry, this future will earmark a significant shift from a niche concept to mass adoption.
Vidu 2.0 Generates Videos in Under 10 Seconds, Without Sacrificing Quality
Until now, bringing this future even remotely within reach was considered unrealistic, as generating a single video could take tens of minutes or hours. With the Vidu 2.0 update, ShengShu Technology once again sets a new global standard for speed, without sacrificing video quality. At the core of this major update is the company's breakthrough full-stack interference accelerator, stemming from its widely cited U-ViT research. In fact, with more than 10 million reference-to-videos generated in its first 100 days, Vidu's 2.0 update is set to offer a rapid, cost-effective solution for on-the-fly A/B testing for creators, editors and brands. Vidu 2.0 empowers small businesses and aspiring editors with tools rivaling top-tier agencies, saving time and money — all within a single platform.
Generating Videos is 55% Cheaper on Vidu 2.0
With continuous improvements rolling out for Vidu, concerns around the rising cost of generating videos is in its heyday. Now, generating clips with Vidu 2.0 is dramatically cheaper than ever before. While the industry's average cost of generating a clip is US $0.084 per second, Vidu has been optimized in this latest 2.0 update to cost an astounding US $0.0375. This is not only 55% less than the industry standard, but also 50% more affordable than Vidu 1.5.
Prompt 'Templates' Lower the Barrier to Entry
Rounding out the latest in major new updates, Vidu also aims to lower the barrier to entry, turning anyone into a one-tap 'prompt engineer.' Vidu 2.0's new "Templates" feature offers a series of pre-set prompt templates that enable users to instantly add detailed actions or interactive props in their generated clips. For instance, in lieu of learning how to write a prompt for an outfit, it can simply be added with just a single click. The library of 'Templates' will be continuously updated to add new one-click prompts.
"Vidu 2.0 represents a significant leap forward in building a complete ecosystem of easy-to-use tools as we embark on the next phase for Vidu, which aims at an untapped opportunity in real-time co-creation," said Jiayu Tang, CEO and co-founder of ShengShu Technology. "Vidu 2.0 features ultra-fast generation speeds, robust multimodal context handling, at a more affordable price that's easier than ever to use. More importantly, these are the cornerstones that enable real-time content to be co-created by users or businesses, enabling them to immerse and better connect with their audiences."
Vidu was the first video generation application to be made commercially available back in July 2024, which stemmed from ShengShu Technology's highly cited research. In fact, the company has been a pioneer, of which the latest innovation was introduced in Vidu 1.5, which unveiled a Multiple-Entity Consistency feature; this enables users to seamlessly blend people, objects, and environments, even if they are completely unrelated, into a cohesive single video.
To learn more about Vidu, please visit
About ShengShu Technology
Founded in March 2023, ShengShu Technology is a leading innovator in deep generative models, specializing in advanced diffusion probabilistic techniques. In 2022, ShengShu introduced the world's first new technical framework, U-ViT, which explores the fusion of Diffusion Models and Transformer architectures for a wide assortment of multimodal generation tasks. ShengShu Technology made the leap from research to commercialization with the launch of its flagship product, Vidu, in July 2024. This AI video generator enables creators to bring their visions to life, whether for art design, game development, film post-production, or social content creation. Our mission is to develop the world's most advanced multimodal generative models, seamlessly integrating text, images, videos, and 3D content. We are at the forefront of applying generative AI to art, design, gaming, filmmaking, and social media, with the goal of enhancing human creativity and productivity.