Recently, Shengshu Technology officially launched the preview version of its new generation video generation flagship model, Vidu Q4Preview. This update brings significant improvements in generation quality, multimodal references, and image accuracy, marking a key step forward for domestic video large models on the path to cinematic quality.

In terms of core features, Vidu Q4Preview fully supports two mainstream modes: image-to-video and reference-based video generation. The image-to-video mode can naturally extend high-quality visuals based on user-provided images and text descriptions; while the reference-based video mode allows generating videos by combining multiple reference images and audio, greatly expanding creators' control options.

image.png

This update has achieved major breakthroughs in multimodal reference capacity and detail control. The model now supports up to three reference audio clips, ensuring consistent voice characteristics for characters in the video through precise audio references. At the same time, it supports up to 15 reference images, providing more comprehensive visual references for facial features, complex scenes, and props, ensuring consistency of elements in long shots and continuous storytelling.

In terms of image quality and shot performance, Vidu Q4Preview further optimizes dynamic camera movement, transition between shots, and the handling of complex shots, significantly enhancing the smoothness and dramatic tension of the video. In terms of specifications, it supports output resolutions up to 2K and 4K, with 10-bit color depth, and can generate videos up to 16 seconds in length, perfectly matching diverse application scenarios such as AI short dramas, advertising marketing, social interaction, and professional film production.

In addition, the official team has introduced flexible specification and pricing plans tailored to different stages of creative needs. The model supports multiple resolutions including 540P, 720P, 1080P, 2K, and 4K, with a promotional price starting at 0.09 yuan per second. Creators can first test their ideas with lower resolution at a lower cost, then directly output high-resolution videos at 2K or 4K once their concepts are mature, achieving high-quality final works with rich details and striking lighting effects.