Skip to content

Seedance 2.5 US Reference to Video

Integrate

Model id bytedance/seedance-2.5/us/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/bytedance/seedance-2.5/us/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"
  }'

# 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"

Up to $6.944 per run charged by actual usage, the rest is refunded Run it on this page

Get API key
ByteDance Reference to Video Native audioReference inputsLipsync4–30 sup to 1080p #stylized#transform

Seedance 2.5 reference video generation, editing and extension from up to 30 images, 10 videos and 10 audios

Made on Doitong

Public works made with Seedance 2.5 US by the Doitong community. Reuse a prompt in one click.

Public works shown: 16
Use the input image as the base scene and visual appearance. Use the reference video strictly as ... Video

Use the input image as the base scene and visual appearance. Use the reference video strictly as a motion reference for the dog’s movement. The dog must move exactly like in the reference video: - same gait (trotting rhythm) - same speed and tempo - same head motion and body dynamics - same ear...

First-person POV of a dog trotting forward along the path at a realistic, moderate speed (approxi... Video

First-person POV of a dog trotting forward along the path at a realistic, moderate speed (approximately 8 km/h). The camera is positioned low, at the natural height of the dog’s head. The motion follows a true trotting gait: steady, rhythmic, grounded movement with gentle vertical bounce and...

Subject: Young woman with dark hair, pale skin, glowing green eyes. Context: Dark, shadowy room. ... Video

Subject: Young woman with dark hair, pale skin, glowing green eyes. Context: Dark, shadowy room. Action: Slow subtle breathing, slight blink. Cold direct gaze at camera. Finger pressed to lips. Minimal movement. Style: Cinematic, hyperrealistic, mysterious, intense. Camera motion: Static shot, no...

First-person POV of a dog running forward along the path at a realistic, moderate speed (approxim... Video

First-person POV of a dog running forward along the path at a realistic, moderate speed (approximately 10 km/h). The camera is positioned low, at the natural height of the dog’s head. The motion follows a true trotting gait: steady, rhythmic, grounded movement with gentle vertical bounce and...

Очень медленный финальный наезд камеры. Пламя свечи на переднем плане горит ярче, создавая блики.... Video

Очень медленный финальный наезд камеры. Пламя свечи на переднем плане горит ярче, создавая блики. Dialogue in this scene: Астролог: "Но в марте будет одна дата… когда решение изменит всё. Напишите в комментариях “Овен” — и я сделаю отдельный разбор." No background music.

A close-up portrait of a striking cyberpunk woman with sleek dark hair partially wet and falling ... Video

A close-up portrait of a striking cyberpunk woman with sleek dark hair partially wet and falling around her face. She’s wearing glossy, high-tech neon visor goggles with a vivid color gradient — bright yellow, orange, and pink reflecting glowing city lights. Her expression is confident and...

Ultra-realistic scene featuring miniature construction workers in orange vests and hard hats, act... Video

Ultra-realistic scene featuring miniature construction workers in orange vests and hard hats, actively working on a giant [pizza]. The tiny workers are using small tools, cranes, and machines to [assemble]. The [pizza] is placed on a metal surface or kitchen countertop. Steam or particles rise...

Slow motion. Low angle camera tilting up at Ilya. Warm light from the kitchen intensifies behind ... Video

Slow motion. Low angle camera tilting up at Ilya. Warm light from the kitchen intensifies behind him, making him look heroic. On-screen dialogue (characters speak with lip-sync): Илья: "Не трогай её!"; Бабушка Нина: "Илья, отойди! Он же…" No background music.

Build a request

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

Text prompt that guides video generation.

video_urls
Drop a file, or

Supply up to 10 reference videos as MP4 or MOV files to guide generation, and identify them in the prompt with @Video1, @Video2, and subsequent numbered labels. Each file must be no larger than 200 MB and last 1.8–30.2 seconds, with all clips together totaling at most 30.2 seconds. Required video properties are 24–60 FPS, a 0.4–2.5 aspect ratio, and 300–6,000 pixels on each side.

duration auto

Video length selection: `auto` delegates the choice to the model using the prompt, while an explicit duration must be from 4 to 30 seconds.

resolution default 720p

Output resolution: 480p prioritizes speed, 720p offers balance, and 1080p delivers high quality.

aspect_ratio default auto

Output aspect ratio: 16:9 gives landscape, 9:16 gives portrait/vertical, 1:1 gives square, and 21:9 gives cinematic ultrawide. Select `auto` for the model to choose the ratio.

Advanced images · audios · task · bitrate_mode · codec · end_user_id · seed
image_urls
Drop a file, or

Image references for video guidance, limited to 30 images and subject to a 50-file maximum across all modalities. Each image may be at most 30 MB and must use JPG, PNG, WebP, BMP, TIFF, GIF, HEIC, or HEIF. Use @Image1, @Image2, and subsequent numbered labels to identify these references in the prompt.

audio_urls
Drop a file, or

Audio references for video guidance have an aggregate duration limit of 30.2 seconds across at most 10 files. Each must use MP3 or WAV, last 1.8–30.2 seconds, and be at most 15 MB. Identify the files in the prompt with @Audio1, @Audio2, and subsequent numbered labels.

task default reference

Video task selection with three behaviors: `reference` guides generation using supplied media, editing changes a reference video, and extension continues one. Both editing and extension automatically set `aspect_ratio` to `auto`; editing also sets `duration` to `auto`.

bitrate_mode default standard

Choose the output encoding bitrate: 'standard' retains the default, whereas 'high' asks the model to improve encoding quality at the expense of a larger file.

codec default auto

Video codec selection: `auto` leaves the default codec behavior unchanged, `H264` selects H.264, and `H265` selects H.265.

Unique identifier assigned to the end user.

Random seed used to make generation reproducible, without guaranteeing exact repetition: reusing it can still yield slightly different results.

POST /run/bytedance/seedance-2.5/us/reference-to-video?wait=20 quote → $6.944
# 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/bytedance/seedance-2.5/us/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"
  }'

# 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 Seedance 2.5 US Reference to Video

A `task` setting switches between reference-guided generation, editing a reference video, and extending one. Accepts up to 30 images, 10 videos and 10 audio files as references, cited as @Image1 and similar. Outputs 480p, 720p or 1080p, auto or 4 to 30 seconds, with aspect ratios from 21:9 to 9:16. Supports `seed` and `bitrate_mode`.

Parameters

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

NameType DefaultAllowed Description
promptoptional
Typestring | null
Text prompt that guides video generation.
taskoptional
Typeenum
Defaultreference
referenceeditingextension
Video task selection with three behaviors: `reference` guides generation using supplied media, editing changes a reference video, and extension continues one. Both editing and extension automatically set `aspect_ratio` to `auto`; editing also sets `duration` to `auto`.
image_urlsoptional images
Typeurl[] · image
Image references for video guidance, limited to 30 images and subject to a 50-file maximum across all modalities. Each image may be at most 30 MB and must use JPG, PNG, WebP, BMP, TIFF, GIF, HEIC, or HEIF. Use @Image1, @Image2, and subsequent numbered labels to identify these references in the prompt.
video_urlsoptional videos
Typeurl[] · video
Supply up to 10 reference videos as MP4 or MOV files to guide generation, and identify them in the prompt with @Video1, @Video2, and subsequent numbered labels. Each file must be no larger than 200 MB and last 1.8–30.2 seconds, with all clips together totaling at most 30.2 seconds. Required video properties are 24–60 FPS, a 0.4–2.5 aspect ratio, and 300–6,000 pixels on each side.
audio_urlsoptional audios
Typeurl[] · audio
Audio references for video guidance have an aggregate duration limit of 30.2 seconds across at most 10 files. Each must use MP3 or WAV, last 1.8–30.2 seconds, and be at most 15 MB. Identify the files in the prompt with @Audio1, @Audio2, and subsequent numbered labels.
resolutionoptional
Typeenum
Default720p
480p720p1080p
Output resolution: 480p prioritizes speed, 720p offers balance, and 1080p delivers high quality.
durationoptional
Typeenum
Defaultauto
auto456789101112131415161718
+12 more192021222324252627282930
Video length selection: `auto` delegates the choice to the model using the prompt, while an explicit duration must be from 4 to 30 seconds.
aspect_ratiooptional
Typeenum
Defaultauto
auto21:916:94:31:13:49:16
Output aspect ratio: 16:9 gives landscape, 9:16 gives portrait/vertical, 1:1 gives square, and 21:9 gives cinematic ultrawide. Select `auto` for the model to choose the ratio.
generate_audiooptional
Typeboolean
Defaulttrue
Enable this to accompany the video with synchronized audio. Generated audio includes speech matched to lip movements, environmental ambience, and sound effects.
bitrate_modeoptional
Typeenum
Defaultstandard
standardhigh
Choose the output encoding bitrate: 'standard' retains the default, whereas 'high' asks the model to improve encoding quality at the expense of a larger file.
codecoptional
Typeenum
Defaultauto
autoH264H265
Video codec selection: `auto` leaves the default codec behavior unchanged, `H264` selects H.264, and `H265` selects H.265.
seedoptional
Typeinteger | null
Random seed used to make generation reproducible, without guaranteeing exact repetition: reusing it can still yield slightly different results.
end_user_idoptional
Typestring | null
Unique identifier assigned to the end user.
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": "bytedance/seedance-2.5/us/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": 6944,
    "usd": "6.944",
    "charged": 6944,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "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
    },
    "seed": 42,
    "draft_id": "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}Video file produced by generation.
seed
integerSeed value applied during generation.
draft_id
string | nullDraft identifier for completion under the same account within seven days; the response contains null instead if draft mode is disabled.

More models: Reference to Video

For AI agents: this page as Markdown is at https://doitong.com/developers/models/bytedance/seedance-2.5/us/reference-to-video.md. All models and guides: https://doitong.com/developers/llms.txt