Skip to content

Wan 3.0 Reference to Video

Integrate

Model id alibaba/wan-3.0/reference-to-video
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/alibaba/wan-3.0/reference-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "The fox from Image 1 runs through the forest from Video 1 at night, fireflies everywhere",
    "resolution": "720p",
    "duration": 5,
    "images": [
      "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
    ]
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

This request: $0.50 500 API credits Run it on this page

Get API key
Alibaba Reference to Video Native audioReference inputs2–30 sup to 1080p #references#long-clips

Builds a 2 to 30 second Wan 3.0 clip from up to 10 images, 5 videos and 5 audio clips.

Made on Doitong

Public works made with Wan 3.0 by the Doitong community. Reuse a prompt in one click.

Public works shown: 2
Create a realistic cinematic UGC-style commercial video, exactly 30 seconds long. The entire scen... Video

Create a realistic cinematic UGC-style commercial video, exactly 30 seconds long. The entire scene takes place inside a modern passenger airplane during a daytime flight. Natural smartphone-like cinematography, realistic airplane cabin, authentic passengers, natural lighting, realistic skin...

Реалистичная бытовая сцена в советской одесской квартире зимним вечером. Женщина находится на кух... Video

Реалистичная бытовая сцена в советской одесской квартире зимним вечером. Женщина находится на кухне, мужчина — в комнате и прихожей. Атмосфера обычной советской семьи перед приходом гостей. Голоса: все персонажи говорят по-русски с естественным, выразительным одесским говором. Характерная...

Build a request

Controls are generated from the model schema. The code and the price update as you change them.

88 / 20000

Describe how to incorporate the reference media, identifying individual references by position within the prompt. For example: 'the subject in Image 1 walks past Video 1'.

reference_image_urls
Drop a file, or · up to 10

Reference image URLs, with a maximum of 10.

resolution

Resolution tier for the resulting video.

aspect_ratio default adaptive

Aspect ratio for the output, with adaptive selection available.

Output length: null enables smart duration based on the prompt and reference media; otherwise, the supplied value specifies seconds.

Advanced videos · audios · file_url · web_url · seed · generate_audio · enable_prompt_expansion · enable_thinking
reference_video_urls
Drop a file, or · up to 5

Supply URLs for reference clips running at 16 fps or higher. The set may contain up to 5 videos, with no more than 15 seconds of footage altogether.

reference_audio_urls
Drop a file, or · up to 5

Reference audio URLs, limited to 5 with a combined duration no greater than 15 seconds.

Drop a file, or

URL of a document used as the basis for the video. Requires enable_thinking to be true.

Webpage URL used as the video's basis, readable only without a login and only with enable_thinking=true.

POST /run/alibaba/wan-3.0/reference-to-video?wait=20 quote → $0.50
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/alibaba/wan-3.0/reference-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "The fox from Image 1 runs through the forest from Video 1 at night, fireflies everywhere",
    "resolution": "720p",
    "duration": 5,
    "images": [
      "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
    ]
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Run this request

Your key stays in this browser: it is sent only to the Doitong API and saved (localStorage) only if you tick Remember. Get an API key

About Wan 3.0 Reference to Video

Wan 3.0 reference-to-video combines reference images, short reference videos (15 seconds in total) and reference audio into one generated clip; address them in the prompt by position (Image 1, Video 1). With the reasoning step on it can also base the video on a document or a public web page. 480p to 1080p, 2 to 30 seconds, generated audio by default.

Parameters

Send either the canonical name or the native name, not both. Canonical names

NameType DefaultAllowed Description
promptoptional
Typestring | null
≤ 20,000 characters
Describe how to incorporate the reference media, identifying individual references by position within the prompt. For example: 'the subject in Image 1 walks past Video 1'.
resolutionoptional
Typeenum
Default1080p
480p720p1080p
Resolution tier for the resulting video.
aspect_ratiooptional
Typeenum
Defaultadaptive
adaptive16:94:31:13:49:16
Aspect ratio for the output, with adaptive selection available.
durationoptional
Typeinteger | null
Default5
2 – 30
Output length: null enables smart duration based on the prompt and reference media; otherwise, the supplied value specifies seconds.
audiooptional generate_audio
Typeboolean
Defaulttrue
Controls whether generated audio is included.
enable_prompt_expansionoptional
Typeboolean
Defaulttrue
Control whether the prompt is intelligently rewritten before generation. Expect a likely quality reduction if you disable rewriting, in exchange for roughly 20–60 seconds less latency.
enable_thinkingoptional
Typeboolean
Defaultfalse
Enables additional reasoning before generation begins.
seedoptional
Typeinteger | null
0 – 2,147,483,647
reference_image_urlsoptional images
Typeurl[] · image
≤ 10 items
Reference image URLs, with a maximum of 10.
reference_video_urlsoptional videos
Typeurl[] · video
≤ 5 items
Supply URLs for reference clips running at 16 fps or higher. The set may contain up to 5 videos, with no more than 15 seconds of footage altogether.
reference_audio_urlsoptional audios
Typeurl[] · audio
≤ 5 items
Reference audio URLs, limited to 5 with a combined duration no greater than 15 seconds.
file_urloptional
Typeurl · file
URL of a document used as the basis for the video. Requires enable_thinking to be true.
web_urloptional
Typestring | null
Webpage URL used as the video's basis, readable only without a login and only with enable_thinking=true.
required Canonical name, also accepted

File parameters take a public https:// URL, a data: URI up to 10 MB, or the file_url of an upload. Files

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "alibaba/wan-3.0/reference-to-video",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 500,
    "usd": "0.50",
    "charged": 500,
    "refunded": 0
  },
  "input": {
    "prompt": "The fox from Image 1 runs through the forest from Video 1 at night, fireflies everywhere",
    "images": [
      "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
    ],
    "duration": 5,
    "resolution": "720p"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200,
      "width": 1024,
      "height": 768,
      "fps": 1.0,
      "duration": 5,
      "num_frames": 1
    },
    "seed": 42,
    "duration": 5,
    "actual_prompt": "string"
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Your files, your choiceEvery outputs[].url is a copy on our storage: kept forever (paid per GB-month) or 7 days for free, by your account setting or ?storage=.
Same shape on every modeltype, url, content_type, width, height and duration, for images, video and audio alike. output is the model’s own result object.
Fields of output
video
object {url, content_type, file_name, file_size, width, height, fps, duration, num_frames}Video file produced by generation.
seed
integerSeed value applied during generation.
duration
numberLength of the generated video, measured in seconds.
actual_prompt
string | null

More models: Reference to Video

For AI agents: this page as Markdown is at https://doitong.com/developers/models/alibaba/wan-3.0/reference-to-video.md. All models and guides: https://doitong.com/developers/llms.txt