#Singapore #AI Video #ShengShu Technology #Vidu Q2

Vidu Launches the Q2 'Reference-to-Video'

ShengShu Technology, a pioneering force in multimodal generative AI, has unveiled Vidu Q2 'Reference-to-Video'. This innovative product is set to redefine the standards of AI-generated content, blending technology and creativity to foster a new era of high-quality, expressive videos. By allowing users to create videos with up to seven reference images of faces, gestures, scenes, or props, the platform significantly enhances the consistency and emotional depth of video productions.

The 'Reference-to-Video' feature enables creators to merge various unrelated elements—like distinct characters, items, or backgrounds—into a single cohesive video. Users can input text prompts, which are processed through Vidu’s Multiple-Entity Consistency feature, ensuring that each component remains true to its unique appearance, even amidst complex scenes. This allows creators to focus on storytelling without the usual errors associated with video creation.

CEO Yihang Luo articulated the groundbreaking potential of Vidu Q2, stating that this release is about empowering AI to mimic human emotions and execute cinematic storytelling. He noted, “This launch is about teaching AI to act and tell stories alongside creators, fundamentally changing the landscape of video generation.”

Enhanced Realism and Cinematic Quality

The Vidu Q2 takes video creation to another level with improved realism, capturing subtle expressions—like a hesitant smile or a curious gaze—with a natural flow that replaces rigid movements typical of AI outputs. Furthermore, it integrates cinematic techniques such as smooth camera shifts, panning, and depth of field adjustments, giving creators the tools to produce videos that not only inform but also evoke emotion.

Each transition between wide shots and close-ups feels seamless, enhancing the storytelling experience. As the platform becomes increasingly adept at interpreting prompts, it captures the intended mood and meaning with greater precision, transforming generative video from a laborious task into a practical daily tool.

Swift Market Adoption Demonstrates Real-World Impact

Alongside the launch, the Vidu Q2 MaaS API is now available globally, allowing businesses to integrate the Reference-to-Video capabilities into their operations. Leveraging its expertise in Reference Generation technology, ShengShu Technology has swiftly partnered with various advertising and e-commerce companies, showcasing the model's impressive output quality and usability.

These adaptations present businesses with innovative avenues to cut costs, enhance efficiency, and boost creative quality. In commercial contexts, the model's consistency ensures clarity in product details, even during complex movements or interactions. Consequently, product advertisements now feature models with natural gestures and micro-expressions, creating video content that is not only realistic but engaging, ultimately redefining the potential of AI-generated media.

A Legacy of Innovation

Since its foundation, ShengShu Technology has continuously led in AI innovation. From introducing groundbreaking architectures like U-ViT in 2022 to the Analytic-DPM framework, which transformed AI processing speeds, each release has established new benchmarks in the industry.

Vidu has undergone several enhancements: Vidu 1.5 introduced multi-character scenes, Vidu 2.0 provided videos at unprecedented costs, and Vidu Q1 integrated cinematic transitions. Vidu Q2 combines these advancements to elevate the platform from mere AI generation to genuine AI performance.

A Rapid Ascent in the Global Landscape

Since the launch of Vidu in April 2024, ShengShu Technology experienced rapid growth, reaching over 200 countries, amassing 30 million users, and generating over 400 million videos, solidifying its position as a key player in creative AI. “With each release, we blend technology and creativity more intricately,” said Luo. “Our objective is not to replace creativity but to expand it, bringing imagination to life and making emotions boundless.”

For further exploration of Vidu’s offerings, visit www.vidu.com and access the Vidu API at platform.vidu.com.

About ShengShu Technology

Founded in March 2023, ShengShu Technology is at the forefront of artificial intelligence, focusing on developing Multimodal Large Language Models. The company's cutting-edge products revolutionize creative production, enabling smarter, quicker, and scalable content creation, reaching applications across interactive entertainment, advertising, film, animation, and cultural tourism globally.