About this model
Wan 3.0 Pro is the image-to-video variant of Alibaba's third-generation Wan video family. You supply a starting frame and a prompt; the model preserves the input image's subject and composition while adding prompt-guided motion, camera movement and scene progression, with optional last-frame guidance to control where the shot ends. It sits alongside the text-driven Wan 3.0 Pro and the multi-asset Wan 3.0 Pro Reference in the same generation stack.
Against its same-family predecessor Wan 2.1 Pro, Alibaba describes several changes versus earlier releases: Wan 3.0 extends single-pass length to 30 seconds, where earlier releases produced clips of a few seconds. Alibaba also describes the generation as omni-modal, accepting a mix of text, images and other assets as conditioning, and highlights preservation of character and reference detail across frames.
Within the 3.0 line, this Pro tier sits alongside the base Wan 3.0 and the Wan 3.0 Prime and Wan 3.0 Prime Pro variants. Per Alibaba's Model Studio API reference, output resolutions span 480p, 720p and 1080p across the supported aspect ratios, and generation is asynchronous: a job is submitted, then polled for the finished video. Access is via the hosted API rather than downloadable weights.
This About section is AI-generated from public sources (Claude Opus 5), with no human editing. It may contain inaccuracies — verify critical details against the sources listed above.
Data sources: Venice API · HuggingFace · Wikipedia — enrichment updated 14h ago