All models
AlibabanewImage → Video

HappyHorse 1.1 · Reference

alibaba/hh1.1-r2v

Estimated

$0.25 / 5s @ 720p

Reference-to-video. Takes 1–9 reference images (characters and scenes) plus a prompt and choreographs them into a single video, keeping each subject's identity consistent.

1–9 images Identity 720p 1080p

Input schema

The exact fields accepted by this model. Values are validated before a generation starts.

imagesimagerequired

1–9 reference images (characters and scenes). Refer to them in the prompt as image 1, image 2…

promptstringrequired

Choreographs the reference images into a single video.

Range: −∞2500

resolutionstringdefault: "720P"

Output resolution.

720P1080P
ratiostringdefault: "16:9"

Aspect ratio of the output.

16:9 · 16:9 · Landscape9:16 · 9:16 · Portrait1:1 · 1:1 · Square4:33:421:9 · 21:9 · Cinematic5:4
durationintegerdefault: 5

Clip length in seconds.

Range: 315

seedinteger

Controls reproducibility. Leave empty for a random seed.

Range: 0+∞

watermarkbooleandefault: false

Adds a Cloudflare watermark.

Default values

{
  "resolution": "720P",
  "ratio": "16:9",
  "duration": 5
}