HappyHorse 1.1 Reference
alibaba/happyhorse-1.1/reference-to-video- 🎬 Reference-to-video model from Alibaba, released June 2026.
- 🆕 Version 1.1 update to the HappyHorse Reference line.
- 👁️ Generates video guided by reference images plus text prompts.
- 🏢 Built by Alibaba, the family behind Qwen and Wan.
- 📅 Launched alongside 1.1 text-to-video and image-to-video siblings.
- 🔧 Reference mode conditions generation on supplied imagery for consistency.
- 📚 Documented through Alibaba Cloud Model Studio's video editing API reference.
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 →HappyHorse 1.1 Reference is the reference-conditioned video generation model in Alibaba's HappyHorse family, released in June 2026. Reference-to-video workflows take one or more reference images alongside a text prompt, letting creators carry a subject, character, or style into newly generated footage — a mode distinct from pure text-to-video or single-image animation. It arrives together with its sibling HappyHorse 1.1 and HappyHorse 1.1 variants, forming a coordinated 1.1 generation.
This release succeeds HappyHorse 1.0 Reference from April 2026, continuing the reference-conditioned line within the broader HappyHorse pipeline. Alibaba Cloud Model Studio documents the family's video editing and reference workflows through its official API reference, which is the authoritative place to confirm supported inputs, modes, and parameters.
Detailed, independently verified specifications for the 1.1 Reference update — parameter count, architecture changes, and benchmark figures specific to this version — were not available in primary sources at the time of writing. Prospective users should confirm capabilities, licensing, and access through Alibaba's official documentation.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
Daily usage · HappyHorse 1.1 Reference · Organic sellers
| Seller | Health | Rep↓ | Sales | Video | Routing | $ / s | $ / video |
|---|---|---|---|---|---|---|---|
| Open Forge 0x1d90…b0aa | healthy | 91.11 | $9.52 | 1.2 min | #1 | $0.14 | — |
"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.