- 🆕 Animates a single still image into video.
- 👁️ Supports first-frame, first-and-last-frame, and video-continuation modes.
- 🎯 Maintains strong subject coherence across frames.
- 🆕 Photorealistic generation within Alibaba's Wan video family.
- 🏢 Developed by Alibaba; newest Wan image-to-video generation.
- ⚡ Released April 2026 as the latest Wan release.
- 📚 Served through Alibaba Cloud Model Studio's image-to-video 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 2.7 is the image-to-video member of Alibaba's Wan family, released in April 2026. Given a first-frame image and a text prompt, it produces smooth, coherent motion, and its image-to-video protocol also supports first-and-last-frame generation and video continuation. The catalog describes photorealistic generation with strong subject coherence across frames, keeping characters and objects consistent throughout a clip.
It is the newest entry in the Wan image-to-video line, succeeding its same-family predecessor Wan 2.6 from December 2025. Both are served through Alibaba Cloud Model Studio's image-to-video API, which documents the first-frame, first-and-last-frame, and video-continuation modes available for animating still images in this generation.
The lineage runs back through Wan 2.5 Preview and Wan 2.1 Pro. Alibaba also ships other 2.7-generation variants spanning multiple input types, including Wan 2.7 for prompt-only text-to-video generation. Always review the version-specific license before commercial use, since terms vary between releases.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
Daily usage · Wan 2.7 · Organic sellers
| Seller | Health | Rep↓ | Sales | Video | Routing | $ / s | $ / video |
|---|---|---|---|---|---|---|---|
| Venice.ai Proxy 0x1f22…18c9 | healthy | 86.84 | $1.70 | 25 s | #1 | $0.0605 | — |
"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.