- 🎬 Video-to-video editing from Alibaba's Wan family
- 🏢 Built by Alibaba, released April 2026
- 🎯 Photorealistic output with strong subject coherence
- 👁️ Transforms source footage while preserving frame consistency
- 🌍 Newest entry in Wan's video-to-video line
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 52 more models by Alibaba Group →Wan 2.7 Edit is Alibaba's video-to-video transformation model, part of the Wan 2.7 generation released in April 2026 and aimed at restyling or modifying existing footage rather than generating clips from scratch. Like the rest of the Wan lineup, it emphasizes photorealistic rendering and strong subject coherence across frames, keeping characters and objects stable as the source video is edited.
Within Alibaba's current catalogue, Wan 2.7 Edit sits alongside a coordinated wave of Wan 2.7 tools: the text-to-video and image-to-video pair both named Wan 2.7, the Wan 2.7 Reference model, and the inpainting-focused Wan 2.7 Pro Edit. It is the current incumbent of the Wan video-to-video line, succeeding earlier generations like Wan 2.6 and the Wan 2.5 Preview, and shares its release wave with Alibaba's broader Wan and Qwen families.
It is best suited for editing and restyling existing video clips where maintaining consistent subjects and a realistic look across frames matters more than synthesizing entirely new scenes — a practical choice for iterative video workflows.
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 Edit · Organic sellers
| Seller | Health | Rep↓ | Sales | Video | Routing | $ / s | $ / video |
|---|---|---|---|---|---|---|---|
| Venice.ai Proxy 0x1f22…18c9 | failingupstream error · 2.5 h | 83.56 | $0.36 | 3 s | #1 | $0.121 | — |
"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.