Alibaba's upgraded real-people motion model. Smoother, more coherent movement through complex action, and characters that stay themselves across the shot. Snaptale reaches for Happy Horse 1.1 the moment a prompt centres on a human moving.
1.1 reworks the motion model and temporal consistency, so multi-beat action — combos, spins, fast footwork — reads as one continuous body instead of a sequence of poses stitched together.
Reference-to-video takes up to nine images and holds the subject, product, and scene across the clip. Pin a face, a costume, a logo — 1.1 keeps them faithful where 1.0 would drift.
Happy Horse 1.1 synthesises diegetic sound — footfall, ambience, dialogue — alongside the visual with tighter audio-visual sync. Snaptale's studio lets you swap the track if you want a different soundtrack on top.
Pin any portrait as the first frame and Happy Horse 1.1 takes it from there — the subject keeps your reference's face, posture and styling while the motion follows your brief, with richer visual detail than 1.0.
Subject framing, headroom, motion arc — all default to vertical when you ask for 9:16. No center-cropping after the fact, no head sliding out of frame on TikTok and Reels.
No model picker, no provider key, no prompt engineering ritual. Describe the shot, the agent picks Happy Horse 1.1 when it fits — and you stay in the conversation while it iterates.
Less "a woman walking", more "runway strut, slow dolly, tight crop on the shoes hitting the line". The more performance language you use, the better the result.
The agent reads the motion verbs (dance, run, strut, jump, throw, glide) and queues Happy Horse 1.1 instead of a generic video model.
Drop the clip on the timeline, snap the beat marker, replace the music. Happy Horse's pacing already gives you something to cut to.
Happy Horse 1.1 is great. Snaptale makes it directable — persistent assets, character locks, the studio and the agent all sharing one project.
Snaptale's studio previews 9:16 by default, with safe-zones that mirror the platforms you'll publish to. No surprise crops at export.
Drop a music track on the timeline and the trim handles snap to the beats Happy Horse composed for — saves the manual nudging.
Generate 4–8 vertical clips on a single brief, line them up as a reel, swap one without re-rendering the rest.
Pin a person to your project once. 1.1's multi-image reference keeps the look, palette and identity faithful across every clip.
1.1 brings stronger motion expressiveness in complex action, much higher consistency from multi-image reference, better instruction following, and richer visual detail with tighter audio sync. Snaptale routes to 1.1 first and keeps 1.0 as a deeper fallback.
Yes. Upload or generate a portrait, pin it to the project, and reference it in your prompt. 1.1 accepts up to nine reference images and holds the subject faithfully across the shot.
Up to 15 seconds, 3s minimum, rendered at 720p with 9:16 native framing. Snaptale's exporter handles the upsample to 1080p without re-rolling the model.
Yes — sound and picture render in the same pass with audio-visual sync. If you'd rather use your own track, mute the generated audio in Snaptale's studio and drop a music file on the timeline.
Seedance shines for cinematic narrative and character continuity across multi-cut stories. Happy Horse 1.1 shines for kinetic, real-people motion you want to scroll past in a feed — and is more forgiving on content other models flag.
Snaptale enforces consent: you can only pin photos you own or have rights to. The model produces likeness-accurate motion of legitimately uploaded subjects, not impersonation of arbitrary public figures.