Wan2.7 Image-to-Video

POST /api/v1/services/aigc/video-generation/video-synthesis — Wan2.7 image-to-video (first frame / first+last / continuation)

The Wan 2.7 image-to-video model accepts multimodal input and covers three jobs: first-frame animation, first+last-frame animation, and video continuation.

Models

Model	Notes
`wan2.7-i2v`	Wan 2.7 image-to-video

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": "wan2.7-i2v",
    "input": {
      "prompt": "A cat rises from the grass and walks toward the sunlight",
      "media": [{ "type": "first_frame", "url": "https://example.com/cat.png" }]
    },
    "parameters": { "resolution": "720P", "duration": 5 }
  }'

Request body

Field	Type	Notes
`model`	string (required)	`wan2.7-i2v`
`input.prompt`	string (optional)	≤5000 characters. Can be omitted when the media speaks for itself
`input.negative_prompt`	string (optional)	≤500 characters (in `input`, not `parameters`)
`input.media`	array (required)	Asset list; combination rules below
`parameters`	object (optional)	Below

Media combinations (the six legal sets; anything else is refused)

Job	media
First frame	`first_frame`
First frame + audio	`first_frame` + `driving_audio`
First + last frame	`first_frame` + `last_frame`
First + last + audio	`first_frame` + `last_frame` + `driving_audio`
Continuation	`first_clip`
Continuation + last frame	`first_clip` + `last_frame`

Each type may appear at most once. Asset limits: images JPEG/JPG/PNG/BMP/WEBP, sides [240, 8000]px, ≤20MB; driving audio wav/mp3, 2–30 s, ≤15MB; first clip mp4/mov, 2–10 s, ≤100MB.

parameters

Parameter	Type	Notes
`resolution`	string	`720P` / `1080P` (default). Sellable tiers follow the price configuration. Output aspect ratio follows the input assets
`duration`	integer	`[2, 15]`, default 5. For continuations this caps the total output duration (a 3 s input + duration 15 → 15 s of output, billed as 15 s)
`prompt_extend`	boolean	Default `true`
`watermark`	boolean	Default `false`
`seed`	integer	`[0, 2147483647]`

Image-to-video has no ratio parameter — the output aspect ratio follows the input assets; sending one is an InvalidParameter error.

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 seconds; continuations by total output duration; 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.