AI Video Generation
Vidu (Shengshu Technology) is an AI video generator for text-to-video, image-to-video, start-end frames, and multi-reference consistency, with strong 2D/anime performance and Q-series models (including Q3 with native audio-video). Offers a creator web app plus a developer API at platform.vidu.com.
Related picks from editorial notes.
Also mentioned
Full overview from our catalog (read-only reference).
Editorial notes to help compare fit before opening the vendor site.
Context from the listing review and editorial research.
NEW tool. Prefer Name "Vidu" (directory slug vidu) over longer "Vidu AI Video Generator". Product also branded Vidu AI. Distinct from unrelated "Vidu" hardware/camera products.
In-depth description and capability notes.
Text-to-video, image-to-video, start-end, and reference-to-video Multi-reference subject consistency Off-peak / non-peak generation modes for cheaper or unlimited-style runs Native audio-video generation on newer Q3 models Lip sync, motion sync, templates, and upscale endpoints (API) Anime / 2D animation strength Separate app subscription credits vs API credits Team/enterprise volume via sales
Creators generate short AI videos with character consistency for social and anime-style content; developers buy API credits to call Vidu models programmatically with per-second pricing by resolution and mode.