Skip to navigation
Authors and ModelsAlibaba Cloud

HappyHorse 1.0

HappyHorse 1.0
Alibaba Cloud · Video Generation
POST /v1/videos/generations

Video model offering Text-to-Video, Image-to-Video, Reference-to-Video, and Video Edit modes with high-fidelity, motion-smooth output.

At a glance

FieldValue
Model idhappyhorse-1-0
Model release date2026-05-06
Input modalitiesText, Image, Video
Output modalitiesVideo
Context window-
Weight precision-
RegionSingapore
Featuresaudio_sync, editing
Native inferenceNo
NewNo
Supported endpointsPOST /v1/videos/generations
Alternate model idsalibaba/happyhorse-1.0, happyhorse-1.0

Pricing

ChargeSpecRate
All Modes 720Pper second$0.14
All Modes 1080Pper second$0.24

Example request

curl https://api.empiriolabs.ai/v1/videos/generations \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "happyhorse-1-0", "prompt": "sunrise over the ocean", "duration": 6}'

Parameters

ParameterTypeRequiredDefaultDescription
promptstringyes-Scene description.
modeenumno"auto"t2v: text-to-video. i2v: animate the attached image. videoedit: edit the attached video. r2v: reference-to-video. · Allowed: auto, t2v, i2v, videoedit, r2v
resolutionenumno"1080p"Output resolution. Larger = higher fidelity but slower / more expensive. · Allowed: 720p, 1080p
durationnumberno5Clip length in seconds. Not used by video edit, which follows the input clip (up to 15 seconds). · Range: 3 – 15
aspect_ratioenumno"16:9"Output aspect ratio for text-to-video and reference-to-video. Image-to-video and video edit follow the input. · Allowed: 16:9, 9:16, 1:1, 4:3, 3:4
imagestringno-Image URL. One for i2v, up to 9 for r2v, and up to 5 optional references for videoedit.
videostringno-Source video URL. Required for videoedit.
seednumberno-Reproducibility seed.
audio_settingenumno"auto"auto: generate native audio. origin: keep the audio of the source video (video edit only). · Allowed: auto, origin
watermarkbooleannofalseAdd a ‘HappyHorse’ watermark to the output.

Notes

Modes (in one model)

  • Text-to-video
  • Image-to-video
  • Reference-to-video
  • Video-to-video Edit (MP4/MOV/WEBM input)

Constraints

  • 720p / 1080p, 3-15s per generation
  • Edit duration matches the input video length

Aspect ratios

  • Text modes: 16:9, 9:16, 1:1
  • Reference mode adds: 4:3, 3:4

Uploaded media preprocessing

  • Video inputs are capped to 15 seconds.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/happyhorse-1-0.