- 🏢 Alibaba's Pro-tier text-to-image model in the Wan 2.7 family.
- 🎯 Photorealistic outputs with strong detail preservation.
- 📏 Supports up to 4K for text-only; 2K for image scenarios.
- 🔧 Multi-reference input and image editing within one model.
- 🆕 Higher-quality tier above standard Wan 2.7 image.
- 🌐 Available via Alibaba Cloud Model Studio API.
- 🔒 Inputs and outputs subject to content moderation.
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 39 more models by Alibaba Group →Wan 2.7 Pro is the higher-quality tier of Alibaba's Wan 2.7 text-to-image line, served through Alibaba Cloud Model Studio. Per the provider's API reference, it is a unified model that combines text-to-image generation, image editing, and multi-reference input within a single endpoint, with the Pro variant positioned for stronger output quality than the standard tier. The catalog describes its outputs as photorealistic with strong detail preservation.
Compared to the standard Wan 2.7, the Pro tier is documented for higher output quality, with Alibaba's API reference noting support up to 4K for text-only generation while image-involved scenarios are recommended to stay at 1K or 2K. It pairs with Wan 2.7 Pro Edit for instruction-driven editing and multi-image composition.
The model accepts multiple reference images for fusion and supports editing workflows alongside straightforward prompt-to-image generation, all addressable through the same documented API. This makes it suited to layout-oriented and composition-heavy creative tasks within Alibaba's image stack.
This image family extends the broader Wan series, which previously centered on video models such as Wan 2.6. As with other Wan endpoints, prompts and generated images are subject to content moderation.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
| Seller | Reputation↓ | Routing | $ / img | Categories | API |
|---|---|---|---|---|---|
| Venice.ai Proxy 0x1f22…18c9 | 100.00 | #2 | $0.0469 | image,creative | openai-images |
| ▲ Apex Ant 0x73b4…e736 | 91.01 | #1 | $0.04 | image,media | openai-images |
| D5V1N2 0xd5e7…7be0 | 33.17 | gated | $0.109 | image,creative,router,fallback | openai-images |
"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 = on-chain trust (0-100). "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.