Skip to content

Wan v2.6 Reference to Video

Integrate

Model id wan/v2.6/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/wan/v2.6/reference-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "videos": [
      "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
    ]
  }'

# 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: $0.75 750 API credits Run it on this page

Get API key
Alibaba Reference to Video Reference inputs5–10 sup to 1080p #reference-to-video

Video generation that keeps subjects from 1 to 3 reference videos, cited as @Video1 to @Video3

Alibaba · Video

Your first result goes here

Build a request below and run it with your API key. Outputs are copied to our storage, kept forever or 7 days for free.

Build a request

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

•required

Prompt of up to 1500 characters, with video subjects identified by @Video1, @Video2, @Video3; subjects may be people, animals, or objects. Multi-shot prompts use this form: '[0-3s] Shot 1. [3-6s] Shot 2.'

•required video_urls
Drop a file, or

Supply 1–3 reference videos to maintain consistent subjects, including people, animals, or objects, and identify them in the prompt with @Video1, @Video2, @Video3. Each video must have at least 16 FPS, last 2 to 30 seconds, and be no larger than 100 MB.

duration 5 s

Set how long the generated video lasts, in seconds. For R2V, choose either 5 or 10 seconds; 15 seconds is not supported.

aspect_ratio default 16:9

Aspect ratio for the output video.

resolution default 1080p

Resolution tier for video output; R2V accepts 720p or 1080p, but not 480p.

Advanced negative_prompt · seed · enable_prompt_expansion · multi_shots · enable_safety_checker
default

Negative prompt specifying unwanted content, limited to 500 characters.

Seed that makes generation reproducible. Setting it to None selects a seed randomly.

POST /run/wan/v2.6/reference-to-video?wait=20 quote → $0.75
# 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/wan/v2.6/reference-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "videos": [
      "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
    ]
  }'

# 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 v2.6 Reference to Video

Generates a clip whose subjects (people, animals or objects) come from 1 to 3 videos in `video_urls`, each at least 16 FPS. The prompt cites them as @Video1, @Video2 and @Video3 and can describe timed shots. `aspect_ratio` offers five choices, `resolution` is 720p or 1080p, and `duration` is 5 or 10 seconds.

Parameters

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

NameType DefaultAllowed Description
promptrequired
Typestring
Prompt of up to 1500 characters, with video subjects identified by @Video1, @Video2, @Video3; subjects may be people, animals, or objects. Multi-shot prompts use this form: '[0-3s] Shot 1. [3-6s] Shot 2.'
video_urlsrequired videos
Typeurl[] · video
Supply 1–3 reference videos to maintain consistent subjects, including people, animals, or objects, and identify them in the prompt with @Video1, @Video2, @Video3. Each video must have at least 16 FPS, last 2 to 30 seconds, and be no larger than 100 MB.
aspect_ratiooptional
Typeenum
Default16:9
16:99:161:14:33:4
Aspect ratio for the output video.
resolutionoptional
Typeenum
Default1080p
720p1080p
Resolution tier for video output; R2V accepts 720p or 1080p, but not 480p.
durationoptional
Typeenum
Default5
510
Set how long the generated video lasts, in seconds. For R2V, choose either 5 or 10 seconds; 15 seconds is not supported.
negative_promptoptional
Typestring | null
Default
Negative prompt specifying unwanted content, limited to 500 characters.
enable_prompt_expansionoptional
Typeboolean
Defaulttrue
Controls whether an LLM rewrites the prompt.
multi_shotsoptional
Typeboolean
Defaulttrue
Shot segmentation control, available only with enable_prompt_expansion set to True. The default true uses intelligent segmentation to build a coherent narrative across shots; false keeps the video as one continuous shot.
seedoptional
Typeinteger | null
Seed that makes generation reproducible. Setting it to None selects a seed randomly.
enable_safety_checkeroptional
Typeboolean
Defaulttrue
Safety-checking switch whose off setting requires account authorization. Without that authorization, every request is checked regardless of the setting; true enables the checker.
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": "wan/v2.6/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": 750,
    "usd": "0.75",
    "charged": 750,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_urls": [
      "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
    ]
  },
  "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,
    "actual_prompt": "Dance battle between Character1 and Character2, cinematic lighting, dynamic camera movement."
  },
  "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}Resulting video file.
seed
integerSeed value used during generation.
actual_prompt
string | nullPrompt actually used when rewriting is enabled.

More models: Reference to Video

For AI agents: this page as Markdown is at https://doitong.com/developers/models/wan/v2.6/reference-to-video.md. All models and guides: https://doitong.com/developers/llms.txt