Vidu AI

Overview

Vidu generates videos from text, images, and reference media in three creation modes — Text to Video, Image to Video (with first/last frame control), and Reference to Video — marketing multi-reference consistency as its key differentiator (up to 15 reference images combinable in the Q4 preview). It includes "My References" for saving characters, props, and scenes for reuse; outputs up to 1080p (cinematic 4K with 10-bit color advertised for the Q4 preview); a Vidu Agent collaborative creation feature; a Vidu App for mobile creation; and a developer/API platform at platform.vidu.com.

On pricing: the official FAQ states "All users receive a set amount of free credits to generate videos at no cost" — Free Plan: Yes. Starting Price is left blank because exact consumer subscription figures were not verifiable on official public pages (third-party figures are conflicting and are not used). ShengShu's own October 7, 2026 press release gives platform/API pricing starting at $0.045 per second of video at 540P, scaling to $0.39 per second at 4K — this is platform/API pricing, not consumer plans.

Web platform with Vidu App for on-the-go creation (advertised on the official site) and a Discord community plus Help Center support. This is ShengShu Technology's mainstream video-generation product — a creative tool, not a face-swap service.