Shengshu Tech Releases Vidu Q4 Preview Video Model Supporting 4K Output

Shengshu Tech has released Vidu Q4 Preview, an upgraded flagship video generation model supporting output resolutions up to 2K and 4K with 10-bit color depth. The model can generate single video clips up to 16 seconds long and accepts up to 3 reference audio tracks and 15 reference images for improved visual and vocal consistency. The release advances multimodal AI video generation by giving creators precise control over character voices, props, and scene consistency across video cuts. Combining high-resolution 4K output with multi-modal inputs substantially lowers production barriers for AI-generated short dramas, commercial advertising, and film production. Vidu Q4 Preview features improved dynamic camera controls, seamless shot cuts, and transitions for both image-to-video and reference-to-video workflows. Promotional pricing starts at 0.09 RMB (~$0.01) per second across multiple resolution tiers (540P to 4K), allowing creators to test scripts affordably at lower resolutions before rendering final high-definition outputs.