- 🏢 Image-to-video model in Alibaba's Wan 3.0 video family
- 🆕 Third-generation Wan Pro tier, following Wan 2.1 Pro
- 📏 Single-pass clips up to 30 seconds, per Alibaba
- 👁️ Animates a supplied first frame, with optional last-frame guidance
- 🎯 Alibaba cites consistent character and reference detail across frames
- 🌐 Outputs at 480p, 720p or 1080p in several aspect ratios
- 🧠 Omni-modal conditioning from text, images and other input assets
- 🔧 Reached through Alibaba Cloud Model Studio's video generation API
Alibaba Group is a Chinese multinational technology company founded in 1999 and headquartered in Hangzhou, Zhejiang. Originally built around e-commerce and cloud computing, Alibaba has become one of the most prolific contributors to open-weight AI research, developing the Qwen…
Explore 51 more models by Alibaba Group →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 via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
| Seller | Rep↓ | Sales | Video | Routing | $ / s | $ / video |
|---|---|---|---|---|---|---|
| ▲ Apex Ant 0x73b4…e736 | 81.71 | — | — | #1 | $0.1065 | — |
"Best price" and the seller table are live Antseed catalog data (advertised $/1M tokens — or $ per generated image for unit-billed image models — not settled amounts). Reputation = buyer trust score (0-100, the Antseed SDK's own formula). "Routing" = the SDK's default buyer routing (what the VPR desktop app ships with): a trust ≥ 60 gate on the effective reputation, then cheapest-first among routable sellers; live failover state (per-peer cooldowns) is buyer-side runtime and not included. Model knowledge (TLDR, provider, About) via the VeniceStats enrichment layer. Advertised catalog, not the model used in any specific purchase. "Usage on Antseed" counts only settlements whose buyers share the per-model split on-chain (metadata v2/v3, opt-in), so every usage figure is a lower bound.