HappyHorse 1.0

Alibaba's video model (from its ATH AI Innovation Unit) that generates video with synchronized audio in a single pass; it topped the Artificial Analysis arena in both text-to-video and image-to-video before its maker was revealed.

🔴 Отдельной страницы анонса у Alibaba не нашёл. Авторство раскрыто самими разработчиками в аккаунте X 10.04.2026 (об этом пишет CNBC). В справочнике уже есть HappyHorse 1.1 (июнь 2026); 1.0 — предыдущая версия, документация Leonardo перечисляет только 1.1.

Understands

text, images, video

Produces

video, speech, sound effects

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.