Reference Video

wan2.7-r2v

Wan 2.7 reference-to-video generation.

Commercial useAsync APIfrom 110 Credits

API reference

Submit this model to the capability endpoint, then poll the returned job until it is terminal. Only the parameters below are accepted.

POST /v1/videos/generations

Required headers

Authorization: Bearer $ARTANY_API_KEY
Content-Type: application/json
Idempotency-Key: unique-request-id

Use a new 8–128 character Idempotency-Key for each logical generation. Retrying the same request with the same key will not double-charge.

Request body

{
  "model": "wan2.7-r2v",
  "prompt": "The person walks through a busy city street",
  "image_with_roles": [
    {
      "url": "https://example.com/reference.jpg",
      "role": "reference_image"
    }
  ],
  "resolution": "1080P",
  "duration": 5,
  "size": "16:9",
  "prompt_extend": true
}

Parameters

Field	Type	Required	Description	Default	Constraints
model	string	Yes	Stable Artany public model ID.	wan2.7-r2v	This exact public model ID.
seed	integer	No	Optional deterministic seed for reproducing a generation when the provider supports it.	—	Range: 0–∞
size	string	No	Requested output image aspect ratio or canvas size. Available values are model-specific.	"16:9"	Allowed: 16:9, 9:16, 1:1, 4:3, 3:4
prompt	string	Yes	Natural-language instruction describing the desired image or video. Include subject, setting, composition, motion, lighting, and style as needed.	—	Length: 0–5000
duration	integer	No	Target generated video length in seconds. Available durations are model-specific and can affect price.	5	Range: 2–15
resolution	string	No	Requested output quality tier. Available values are model-specific and can affect price.	"1080P"	Allowed: 720P, 1080P
video_urls	array (string items)	No	Public video URLs used as the source or reference video for a supported video workflow.	—	Items: 1–5
prompt_extend	boolean	No	Whether to let the model expand the prompt before generation.	true	—
negative_prompt	string	No	Elements, styles, or visual characteristics to avoid in the generated result.	—	Length: 1–500
image_with_roles	array (object items)	No	Role-labelled reference images used by a model that supports character or subject consistency.	—	Items: 1–5

Accepted response

The submit endpoint returns HTTP 202 with a normalized job. Poll GET /v1/jobs/{jobId} until the status is terminal.

{
  "id": "job_…",
  "object": "generation.job",
  "model": "wan2.7-r2v",
  "status": "queued",
  "progress": 0,
  "output": null,
  "error": null,
  "billing": {
    "estimated_credits": "110",
    "frozen_credits": "…",
    "charged_credits": "0",
    "state": "frozen",
    "price_version": "2026-07-18.picverse-parity"
  },
  "created_at": "2026-07-21T00:00:00.000Z",
  "completed_at": null
}

Lifecycle and failures

queued / running — wait and poll again.
succeeded — read output URLs from output; the actual charge is settled.
failed / canceled — inspect error; frozen Credits are released.
For a schema error, the API returns an error object and identifies the invalid field in param when applicable.

Input

Modelprompt*image_with_rolesvideo_urlsnegative_promptresolutiondurationsizeprompt_extendseed

Runs are billed to your Credits at the listed price — same engine as the public API.

Output

Run the model to see results here

Integrate in minutes

curl -X POST "https://api.artany.ai/v1/videos/generations" \
  -H "Authorization: Bearer $ARTANY_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: unique-request-id" \
  -d '{"model":"wan2.7-r2v","prompt":"The person walks through a busy city street","image_with_roles":[{"url":"https://example.com/reference.jpg","role":"reference_image"}],"resolution":"1080P","duration":5,"size":"16:9","prompt_extend":true}'

# poll until terminal
curl "https://api.artany.ai/v1/jobs/{job_id}" \
  -H "Authorization: Bearer $ARTANY_API_KEY"