Skip to main content

HappyHorse 1.1 API

Uncensored — This model declares no content filter. SpicyAPI forwards the request without adding a platform content scan; legal and consent duties remain with the customer. Image to video — Uncensored; Reference to video — Uncensored; Text to video — Filtered.Browse every model at this filtering level
alibaba/happyhorse-1.1/image-to-video

HappyHorse 1.1 image-to-video animates your opening frame from a prompt describing the movement that follows. Clips run 3 to 15 whole seconds at 720p or 1080p with generated sound, and the frame sets the shape.

Filtering differs by endpoint: Image to video — Uncensored, Reference to video — Uncensored, Text to video — Filtered.

From $0.14/s
Run model

Workbench

These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.

  • Output5s
    andalusian-plaza-flamenco-glance

    `image_url` is a sunset plaza in Andalusia: whitewashed arcades, string lights, a clapping crowd in a wide circle and two guitarists, with a woman in a rose-pink off-the-shoulder flamenco gown with tiered ruffles and a high slit posed mid-dance in the centre. The clip opens on that frame and follows the prompt: she turns away on the spot with one arm curved overhead while her other hand sweeps the ruffled hem out in a low swirl across the stones, then she stops side-on and looks back over her shoulder into the lens with a slow smile as the camera pushes in. This endpoint has no aspect-ratio field, so the 16:9 still sets the frame; `duration_seconds` is `5` at `720p`.

    • 720p
    • 5s
  • Output5s
    wasteland-hood-two

    The opening frame decides the shape here — there is no `aspect_ratio` field on this endpoint, so the still you hand in sets the frame of the clip. The prompt is then written only for things that exist in motion: cloth lifted and dropped by the wind, a rippling heat haze, dust crossing the road. That is the division of labour on an image-to-video call, and it is why the sentence never describes the composition.

    • 1080p
  • Output6s
    tailgate-turn

    One still and a movement note. The wardrobe, the truck and the backlight are decided by the frame, not by the words.

    • 1080p
    • 6s
  • Output4s
    quiet-hold

    Four seconds of near-stillness - the shape that works best when there is no closing frame to aim at.

    • 720p
    • 4s

This example starts at $0.14 per output second. The Playground updates the estimate when you change the settings.