Reference Video

wan2.7-r2v

Wan 2.7 reference-to-video generation.

POST /v1/videos/generationsAsync generation

Quick start

Submit a request with this public model ID. The API immediately returns a normalized job; poll GET /v1/jobs/{jobId} while its status is queued or running.

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}'

Request

Headers

Header	Required	Description
Authorization	Yes	Bearer token for an Artany API key.
Content-Type	Yes	Must be application/json.
Idempotency-Key	Recommended	8–128 characters. Reusing it with an identical request prevents duplicate jobs and charges.

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
}

Request Parameters

Only fields in this model’s public request contract are shown. Defaults are applied before validation and quoting.

Note:Reference-to-video workflow. Supply the supported reference inputs, then use prompt to describe the intended scene and motion.

modelstringrequireddefault: "wan2.7-r2v"

Stable public model ID for this request.

promptstringrequired

Instruction for the generated video. Describe the desired motion and scene while preserving the supplied references.

Length: 0–5000

image_with_rolesarray<object>

Role-labelled image references for subject and frame consistency.

Items: 1–5

Field description

url: Image URL.
role: Supported reference role for this workflow.

video_urlsarray<string>

Reference videos that condition generation.

Items: 1–5

negative_promptstring

Content or visual characteristics to avoid.

Length: 1–500

resolutionstringdefault: "1080P"

Output resolution tier.

Allowed: 720P, 1080P

720P1080P

durationintegerdefault: 5

Requested video duration in seconds.

Range: 2–15

sizestringdefault: "16:9"

Output framing for the supported workflow.

Allowed: 16:9, 9:16, 1:1, 4:3, 3:4

16:99:161:14:33:4

prompt_extendbooleandefault: true

Whether to enrich the prompt before generation.

seedinteger

Optional seed that influences generation randomness.

Range: 0–∞

Use Cases

Choose the request shape that matches the source media you provide. The examples use the public model ID and accepted public fields.

Reference-to-video

Use the supplied reference media and a motion instruction.

{
  "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"
    }
  ],
  "video_urls": [
    "https://example.com/reference.mp4"
  ],
  "duration": 5,
  "resolution": "1080P"
}

Response and task status

A successful asynchronous submission returns HTTP 202 with a supplier-neutral job.

{
  "id": "job_…",
  "object": "generation.job",
  "model": "wan2.7-r2v",
  "status": "queued",
  "progress": 0,
  "output": null,
  "error": null,
  "billing": {
    "estimated_credits": "…",
    "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
}

queued / running: continue polling.
succeeded: retrieve media URLs from output; billing has settled.
failed / canceled: inspect error; frozen Credits are released.