Vidu

Vidu is an AI video generator from Shengshu Technology that creates short cinematic clips from text prompts, images, or up to seven reference photos, with companion image and sound tools. Its Q3 model generates up to 16 seconds of continuous 1080p video at 24fps in a single pass and outputs synchronized native audio and video together. Reference-to-video keeps characters, objects, and environments consistent across a shot. Pricing is credit-based and affordable, making it popular with creators and marketers producing short-form video.

Vidu is a generative video platform built by Shengshu Technology, a Beijing-based startup founded by Tsinghua University researchers. It converts text prompts, still images, or a set of reference photos into short video clips, and offers companion image and sound-effect generation. Modes include text-to-video, image-to-video, and a reference-to-video mode where you upload up to seven reference images of characters, objects, and environments and the model keeps them consistent across the shot. Vidu's Q3 model is a standout for two reasons: it can generate up to 16 seconds of continuous 1080p video at 24fps in a single pass, among the longest continuous windows of leading tools, and it was among the first to output synchronized native audio and video together, rather than requiring separate voiceover or sound stitching. Shengshu has raised substantial capital, including a large Series B led by Alibaba Cloud in 2026, and has been reported as a high-valuation AI video contender. Vidu's pricing is credit-based and affordable, making it attractive to creators and marketers producing short-form video who value clip length, character consistency, and built-in audio.