HappyHorse Video Editing

POST /api/v1/services/aigc/video-generation/video-synthesis — edit a video guided by an instruction and reference images

The HappyHorse video-editing model takes an input video plus optional reference images and performs instruction-driven edits — style transfer, local replacement, and similar.

Models

Model	Notes
`happyhorse-1.0-video-edit`	Video editing
`happyhorse-1.0-video-edit-20260618`	Video editing, 20260618 snapshot

Create a job

POST/api/v1/services/aigc/video-generation/video-synthesis

curl https://api.modelsite.ai/api/v1/services/aigc/video-generation/video-synthesis \
  -H "Authorization: Bearer $MODELSITE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "happyhorse-1.0-video-edit",
    "input": {
      "prompt": "Dress the character in the striped sweater from the reference image",
      "media": [
        { "type": "video", "url": "https://example.com/input.mp4" },
        { "type": "reference_image", "url": "https://example.com/sweater.webp" }
      ]
    },
    "parameters": { "resolution": "720P" }
  }'

Request body

Field	Type	Notes
`model`	string (required)	Fixed to `happyhorse-1.0-video-edit`
`input.prompt`	string (required)	The editing instruction (style transfer, local replacement, …). CJK counts as 2, everything else as 1, budget 5000
`input.media`	array (required)	Exactly 1 `video` entry (required) + 0–5 `reference_image` entries (optional)
`parameters`	object (optional)	Below

parameters

Parameter	Type	Notes
`resolution`	string	`720P` / `1080P` (default). Sellable tiers follow the price configuration
`watermark`	boolean	Defaults to `true`; pass `false` explicitly to opt out
`audio_setting`	string	Sound control: `auto` (default, model decides) / `origin` (keep the source audio)
`seed`	integer	`[0, 2147483647]`

Asset requirements

Input video: MP4 / MOV (H.264 recommended), 3–60 s, short side ≥360px and long side ≤4096px, aspect ratio 1:2.5–2.5:1, ≤100MB, 8–60 fps
Reference images: JPEG / JPG / PNG / WEBP, both sides ≥300px, aspect ratio 1:2.5–2.5:1, ≤20MB

Output duration is 3–15 seconds: inputs at or under 15 s keep their duration; longer inputs are trimmed to the first 15 seconds.

Polling and result

GET/api/v1/tasks/{task_id}

curl "https://api.modelsite.ai/api/v1/tasks/$TASK_ID" \
  -H "Authorization: Bearer $MODELSITE_API_KEY"

Response fields

Field	Meaning
`output.task_id`	Job ID (same value returned at creation)
`output.task_status`	`PENDING` queued / `RUNNING` processing / `SUCCEEDED` done / `FAILED` failed
`output.video_url`	The generated video URL — only on `SUCCEEDED`; download promptly
`output.code` / `output.message`	Present only on failure, with the reason
`usage`	Usage stats (duration, resolution tier, …); counted only on success
`request_id`	Unique request ID — include it when reporting issues

Status flow: PENDING → RUNNING → SUCCEEDED / FAILED.

Billing

Billed by actual generated duration (fractional seconds); failed jobs are not billed. Rates on the Models page.

Error handling

Creation-time errors return {"code": "...", "message": "..."}; mid-job failures surface through the poll's output.code / output.message. General error codes: Errors.