HappyHorse 1.1

• 🎬 Text-to-video generation model from Alibaba
• 🎯 Current version of the HappyHorse text-to-video line
• 🆕 Latest 1.1 generation, released mid-2026
• 🏢 Part of Alibaba's broad generative media lineup
• 💬 Turns text prompts directly into video clips

Alibaba

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,…

HappyHorse 1.1 is Alibaba's text-to-video generator, taking written prompts and synthesizing them into motion clips without any source image. Released in June 2026, it succeeds HappyHorse 1.0 (April 2026) and stands as the current incumbent of the HappyHorse text-to-video line, bringing refinements over the prior generation while keeping the same prompt-driven workflow.

The 1.1 release arrived as a coordinated update across the HappyHorse family, alongside its image-to-video counterpart HappyHorse 1.1 and the reference-conditioned HappyHorse 1.1 Reference. Together these cover the common video creation entry points — pure text, an input frame, or a reference subject — and sit beside Alibaba's larger Wan video series and Qwen image and text models in a deep generative catalogue.

Best suited for creators who want to generate short video from a text description alone, HappyHorse 1.1 fits storyboarding, concept visualization, and quick motion experiments where no starting image is available. Users who need to animate an existing picture or preserve a reference subject can reach for the matching image-to-video or reference variants instead.