Shengshu Technology has just rolled out the preview version of its latest flagship model for video generation—Vidu Q4 Preview. This iteration places a premium on refining character performances, camera movements, and the execution of complex visual effects.

Priced attractively at an introductory rate of just 0.09 yuan per second, Vidu Q4 Preview offers a range of output specifications. This allows users to generate up to five times more content without exceeding their original budget. Despite the cost reduction, the model boasts enhanced vividness and expressiveness, supporting features like multi-reference images, reference audio, and high-definition output.

This makes state-of-the-art video generation tools more accessible to individual creators and small teams, enabling them to engage in frequent creative experimentation at a lower cost. It marks a significant shift, moving these models from being showcased in a handful of selected samples to becoming integral parts of daily creative workflows. This transition opens up possibilities across various industrial sectors, including advertising, e-commerce, comic dramas, short films, and film and television production.

At present, the competition among domestic video generation models has evolved beyond mere technological advancements. It now hinges on production capabilities, with a focus on aspects such as controllability, consistency, and overall production costs. Shengshu Technology is committed to transforming model capabilities into tangible, practical products. The preview version of Vidu Q4 will undergo continuous refinement based on user feedback, propelling video generation technology towards even more widespread creative applications.