HappyHorse 1.1 AI video generator

HappyHorse 1.1 is a video model from Alibaba, released in June 2026 as the upgrade to HappyHorse 1.0. It generates picture and sound together, including dialogue with lip-sync, in clips of up to 15 seconds.

HappyHorse 1.1, released by Alibaba in June 2026, moves more smoothly in complex action, follows instructions more closely, adds richer detail and keeps sound and picture in tighter sync than HappyHorse 1.0 from April 2026. It also reads several reference images better, a mode DreamBench doesn’t use. DreamBench runs 1.1.

Yes. HappyHorse 1.1 generates dialogue with lip-sync as part of the clip, along with ambient sound and the voice’s performance, so a presenter, a vlogger or a character in a drama can speak straight to camera. On DreamBench, write the line in quotation marks, say who speaks it, and keep it short enough to finish inside a 15-second clip: a line that runs past the clip’s end gets cut or hurried, so give that scene new direction if the lip-sync misses.

Each clip HappyHorse 1.1 generates runs up to 15 seconds. A whole DreamBench video can be longer, up to 5 minutes depending on your plan, because DreamBench plans the scenes and joins the clips into one video.

HappyHorse 1.1 renders at 720p or 1080p on DreamBench, your choice. You can make it square (1:1), widescreen (16:9), portrait (9:16), 4:3 or cinematic 21:9.

Yes. On DreamBench every HappyHorse 1.1 clip comes with sound generated together with the picture, from dialogue to ambient noise, so describe what should be heard as well as what should be seen.

HappyHorse 1.1 uses credits for each second of video, plus a base amount per video, at a rate that depends on the resolution. The table on this page shows the current rates, and you always see the exact cost before you generate.

Yes. On DreamBench, each HappyHorse 1.1 video uses credits for every second plus a base amount per video, and credits come with a paid plan, with HappyHorse 1.1 on every plan. Every clip comes with sound, and the composer shows the exact cost before you generate.

Say who speaks, put the words in quotation marks, then describe the setting, light and camera. Keep each clip to one setting: HappyHorse 1.1 doesn’t cut partway through a clip, so a longer video joins several clips.

Yes, up to 8 per video. DreamBench turns them into each clip’s opening frame, which HappyHorse 1.1 animates. Alibaba’s multi-image reference-to-video mode is not what DreamBench runs.

Both generate lip-synced dialogue on DreamBench, so run the same brief on each and keep the one you prefer. HappyHorse 1.1 runs up to 15 seconds a clip at 720p or 1080p, in 5 aspect ratios; the Kling 3.0 page, linked below, states its own limits.

No. DreamBench offers HappyHorse 1.1 through its composer, in the browser on a phone, tablet or computer, with nothing to install. Developers can use Alibaba’s own API on its Model Studio platform, where the prices and limits are Alibaba’s, not DreamBench’s.

Videos made on the Starter plan carry a small DreamBench watermark; Plus, Ultra and Studio remove it. The sound and picture are otherwise as HappyHorse 1.1 generated them.

Yes. DreamBench’s Terms of Use allow personal and commercial use, including ads and client work. You need the rights to anything you upload.

Available on every plan. Video length depends on the plan: up to 30 seconds on Starter, 2 minutes on Plus and 5 minutes on Ultra and Studio.

5: 1:1, 16:9, 9:16, 4:3 and 21:9. Pick the ratio in the composer, or name it in the prompt and DreamBench sets it for you.

Press Create with HappyHorse 1.1, or pick it in the composer, and describe the video you have in mind. DreamBench writes the scene plan, generates every scene with HappyHorse 1.1 and joins them into one video. Then give any scene new direction and keep the rest.