Wan 3.0 Text-to-Video is built on Alibaba Wan 3.0 all-in-one video model (wan3.0-video). Generate coherent, naturally lit video from a text prompt only, with no reference image or video. Output is natively up to 30 seconds with smart duration, 480P/720P/1080P, adaptive aspect ratio and optional audio.
Text-Only Video GenerationNative Up to 30sSmart Duration480P/720P/1080PAdaptive RatioControllable Audio OutputUltra-Realistic Rendering