Skip to content

Seedance 2.0 Fast Reference to Video

Integrate

Model id bytedance/seedance-2.0/fast/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-2.0/fast/reference-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Create an ultra-realistic cinematic video of a beautiful black-and-white Siberian Husky with striking blue eyes exploring a snowy mountain landscape at sunset. The environment features pristine white snow, snow-covered pine trees, enormous snow-covered rocks, distant blue mountains, and warm golden sunlight illuminating the snow. Every animal must look completely realistic, with detailed fur, natural movements, and believable interactions.\n\nSCENE 1 — THE HUSKY APPROACHES \nA beautiful black-and-white Siberian Husky walks slowly through deep, powdery snow. Its paws sink naturally into the snow, sending tiny snow particles into the air. The camera follows the dog from a low angle as it lowers its head and sniffs the ground curiously. Warm sunset light illuminates its fur.\n\nSCENE 2 — SOMETHING MOVES \nThe Husky suddenly notices movement near a large snow-covered rock. It stops, raises its head, and turns its blue eyes toward the rock. Its ears stand upright, and its nose twitches as it investigates. The camera smoothly moves closer to capture its curious expression.\n\nSCENE 3 — THE SURPRISE \nA tiny, fluffy brown bunny cautiously peeks out from behind the rock. A second, smaller white bunny appears just behind it. Both rabbits have realistic fur, twitching noses, upright ears, and tiny paws. The Husky watches them with curiosity while maintaining a natural, relaxed posture.\n\nSCENE 4 — THE ADORABLE MOMENT \nThe brown bunny hops forward through the fresh snow, followed by the tiny white bunny. The Husky gently lowers its head toward them, sniffing the snow nearby. The rabbits pause and look toward the dog. Their contrasting sizes create a beautiful cinematic composition.\n\nSCENE 5 — THE HEARTWARMING ENDING \nBoth bunnies hop closer to the Husky. The dog remains calm and gently tilts its head, watching their movements with curious blue eyes. The camera slowly pulls back to reveal the three animals together in the glowing snowy landscape, surrounded by majestic mountains and warm sunset light.\n\n🎥 Camera & Quality Instructions\n\nPhotorealistic animal fur, eyes, whiskers, paws, and facial expressions.\n\nNatural animal anatomy and believable movement.\n\nSmooth cinematic tracking shots with realistic depth of field.\n\nGolden-hour lighting with cool blue shadows across the snow.\n\nRealistic snow particles, pawprints, and subtle wind.\n\nNatural ambient audio: soft winter wind, paws crunching in snow, and gentle rabbit movements.\n\nNo dialogue, text, subtitles, logos, or watermarks.\n\nNo cartoon appearance, artificial CGI look, distorted anatomy, duplicated animals, or sudden scene transitions.\n\nMaintain consistent animal appearances throughout the entire video.",
    "images": [
      "https://content.doitong.com/dev-api/2026/10/21/req_8iod92yjmwgt23lnwd9b32aw/0-tum_e2KxIyKfiLcxMKSh9_WqMV3cYt.png"
    ],
    "resolution": "480p",
    "duration": "5",
    "aspect_ratio": "16:9",
    "generate_audio": true
  }'

# 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: $0.565 565 API credits Run it on this page

Get API key
ByteDance Reference to Video Native audioReference inputsFast4–15 sup to 720p #references

The quicker, cheaper Seedance 2.0 multi-reference mode, 480p or 720p with sound.

Examples

Input
Output · ~187 s

PromptCreate an ultra-realistic cinematic video of a beautiful black-and-white Siberian Husky with striking blue eyes exploring a snowy mountain landscape at sunset. The environment features pristine white snow, snow-covered pine trees, enormous snow-covered rocks, distant blue mountains, and warm golden sunlight illuminating the snow. Every animal must look completely realistic, with detailed fur, natural movements, and believable interactions. SCENE 1 — THE HUSKY APPROACHES A beautiful black-and-white Siberian Husky walks slowly through deep, powdery snow. Its paws sink naturally into the snow, sending tiny snow particles into the air. The camera follows the dog from a low angle as it lowers its head and sniffs the ground curiously. Warm sunset light illuminates its fur. SCENE 2 — SOMETHING MOVES The Husky suddenly notices movement near a large snow-covered rock. It stops, raises its head, and turns its blue eyes toward the rock. Its ears stand upright, and its nose twitches as it investigates. The camera smoothly moves closer to capture its curious expression. SCENE 3 — THE SURPRISE A tiny, fluffy brown bunny cautiously peeks out from behind the rock. A second, smaller white bunny appears just behind it. Both rabbits have realistic fur, twitching noses, upright ears, and tiny paws. The Husky watches them with curiosity while maintaining a natural, relaxed posture. SCENE 4 — THE ADORABLE MOMENT The brown bunny hops forward through the fresh snow, followed by the tiny white bunny. The Husky gently lowers its head toward them, sniffing the snow nearby. The rabbits pause and look toward the dog. Their contrasting sizes create a beautiful cinematic composition. SCENE 5 — THE HEARTWARMING ENDING Both bunnies hop closer to the Husky. The dog remains calm and gently tilts its head, watching their movements with curious blue eyes. The camera slowly pulls back to reveal the three animals together in the glowing snowy landscape, surrounded by majestic mountains and warm sunset light. 🎥 Camera & Quality Instructions Photorealistic animal fur, eyes, whiskers, paws, and facial expressions. Natural animal anatomy and believable movement. Smooth cinematic tracking shots with realistic depth of field. Golden-hour lighting with cool blue shadows across the snow. Realistic snow particles, pawprints, and subtle wind. Natural ambient audio: soft winter wind, paws crunching in snow, and gentle rabbit movements. No dialogue, text, subtitles, logos, or watermarks. No cartoon appearance, artificial CGI look, distorted anatomy, duplicated animals, or sudden scene transitions. Maintain consistent animal appearances throughout the entire video.

5 s480p16:9generate_audio: true$0.565 · 565 API credits

Prompt from @RizwanAly07 on X

Build a request

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

•required

Text prompt that guides video generation.

image_urls
Drop a file, or · up to 9

Image references for video guidance, limited to 9 images and subject to a 12-file maximum across all modalities. Each image may be at most 30 MB and must use JPEG, PNG, or WebP. Use @Image1, @Image2, and subsequent numbered labels to identify these references in the prompt.

video_urls
Drop a file, or · up to 3

Video references for generation, supplied as MP4 or MOV files and identified in the prompt by @Video1, @Video2, and subsequent numbered labels. Each must have a resolution from approximately 480p (640x640) to approximately 720p (834x1112). The set is limited to 3 videos totaling less than 50 MB, with an aggregate duration from 2 to 15 seconds.

duration 5 s

Video length selection: `auto` delegates the choice to the model using the prompt, while an explicit duration must be from 4 to 15 seconds.

resolution

Output resolution: 480p favors generation speed, while 720p offers a balanced choice.

aspect_ratio

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 audios · bitrate_mode · codec
audio_urls
Drop a file, or · up to 3

Audio references for video guidance require at least one accompanying image or video reference. Supply MP3 or WAV files of at most 15 MB each, with no more than 3 files and an aggregate duration capped at 15 seconds. Identify them in the prompt using @Audio1, @Audio2, and subsequent numbered labels.

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.

POST /run/bytedance/seedance-2.0/fast/reference-to-video?wait=20 quote → $0.565
# 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-2.0/fast/reference-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Create an ultra-realistic cinematic video of a beautiful black-and-white Siberian Husky with striking blue eyes exploring a snowy mountain landscape at sunset. The environment features pristine white snow, snow-covered pine trees, enormous snow-covered rocks, distant blue mountains, and warm golden sunlight illuminating the snow. Every animal must look completely realistic, with detailed fur, natural movements, and believable interactions.\n\nSCENE 1 — THE HUSKY APPROACHES \nA beautiful black-and-white Siberian Husky walks slowly through deep, powdery snow. Its paws sink naturally into the snow, sending tiny snow particles into the air. The camera follows the dog from a low angle as it lowers its head and sniffs the ground curiously. Warm sunset light illuminates its fur.\n\nSCENE 2 — SOMETHING MOVES \nThe Husky suddenly notices movement near a large snow-covered rock. It stops, raises its head, and turns its blue eyes toward the rock. Its ears stand upright, and its nose twitches as it investigates. The camera smoothly moves closer to capture its curious expression.\n\nSCENE 3 — THE SURPRISE \nA tiny, fluffy brown bunny cautiously peeks out from behind the rock. A second, smaller white bunny appears just behind it. Both rabbits have realistic fur, twitching noses, upright ears, and tiny paws. The Husky watches them with curiosity while maintaining a natural, relaxed posture.\n\nSCENE 4 — THE ADORABLE MOMENT \nThe brown bunny hops forward through the fresh snow, followed by the tiny white bunny. The Husky gently lowers its head toward them, sniffing the snow nearby. The rabbits pause and look toward the dog. Their contrasting sizes create a beautiful cinematic composition.\n\nSCENE 5 — THE HEARTWARMING ENDING \nBoth bunnies hop closer to the Husky. The dog remains calm and gently tilts its head, watching their movements with curious blue eyes. The camera slowly pulls back to reveal the three animals together in the glowing snowy landscape, surrounded by majestic mountains and warm sunset light.\n\n🎥 Camera & Quality Instructions\n\nPhotorealistic animal fur, eyes, whiskers, paws, and facial expressions.\n\nNatural animal anatomy and believable movement.\n\nSmooth cinematic tracking shots with realistic depth of field.\n\nGolden-hour lighting with cool blue shadows across the snow.\n\nRealistic snow particles, pawprints, and subtle wind.\n\nNatural ambient audio: soft winter wind, paws crunching in snow, and gentle rabbit movements.\n\nNo dialogue, text, subtitles, logos, or watermarks.\n\nNo cartoon appearance, artificial CGI look, distorted anatomy, duplicated animals, or sudden scene transitions.\n\nMaintain consistent animal appearances throughout the entire video.",
    "images": [
      "https://content.doitong.com/dev-api/2026/10/21/req_8iod92yjmwgt23lnwd9b32aw/0-tum_e2KxIyKfiLcxMKSh9_WqMV3cYt.png"
    ],
    "resolution": "480p",
    "duration": "5",
    "aspect_ratio": "16:9",
    "generate_audio": true
  }'

# 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

Made on Doitong

Public works made with Seedance 2.0 by the Doitong community. Reuse a prompt in one click.

Public works shown: 16
Subject: Man in a bunny suit, frozen city crowd Context: Urban street, all people, vehicles, and ... Video

Subject: Man in a bunny suit, frozen city crowd Context: Urban street, all people, vehicles, and trees are frozen mid-action Action: Only the bunny-suited man moves, walking and waving in front of an unresponsive man in a black suit Style: Cinematic, intense stillness, Quicksilver/X-Men, Matrix...

This is a cinematic scene filmed with a hand-held shaky camera. The entire world is completely fr... Video

This is a cinematic scene filmed with a hand-held shaky camera. The entire world is completely frozen in time. Nothing moves. Absolutely nothing. All people are frozen, cars are frozen, bicycles are frozen, traffic lights are frozen, trees and leaves are frozen, wind is frozen, shadows are...

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...

Аня вздрагивает от трезвона десяти будильников, резко садится в кровати, хлопает по ним руками в ... Video

Аня вздрагивает от трезвона десяти будильников, резко садится в кровати, хлопает по ним руками в попытке выключить, но они продолжают пищать, она в панике оглядывается. Камера медленно приближается с низкого угла от ног кровати к лицу, создавая ощущение нарастания хаоса. Лучи утреннего солнца...

Анна мягко гладит спящую собаку и смотрит на заходящее солнце с усталой, но счастливой улыбкой. К... Video

Анна мягко гладит спящую собаку и смотрит на заходящее солнце с усталой, но счастливой улыбкой. Камера медленно отъезжает назад, охватывая весь уютный дом и сад. Свет солнца постепенно затухает, переходя в сумерки. Финальный кадр передает чувство семейного тепла и завершенности прекрасного дня....

Аня падает на корточки у двери, лихорадочно надевает разные носки, роняет помаду из сумки, вскаки... Video

Аня падает на корточки у двери, лихорадочно надевает разные носки, роняет помаду из сумки, вскакивает, хватает ключи. Камера кружит вокруг нее на 180 градусов на уровне колен, ускоряясь. Ключи звенят, сумка болтается. Эмоциональный бит — пик хаоса с ноткой абсурдного юмора. Dialogue in this...

Буня несется во весь опор, виляя хвостом, сосиска забавно болтается у него в пасти. Камера быстро... Video

Буня несется во весь опор, виляя хвостом, сосиска забавно болтается у него в пасти. Камера быстро следует за ним на уровне земли, создавая эффект скорости. Анна и дети вбегают в кадр и выбегают из него, размахивая руками. Пыль слегка поднимается из-под лап. Сцена наполнена комичным драйвом и...

About Seedance 2.0 Fast Reference to Video

Reference up to 9 images, 3 videos and 3 audio clips as @Image1, @Video1, @Audio1 in the prompt and get a 4 to 15 second scene with synchronized sound at 480p or 720p. At least one image or video is required, at most 12 files in total; reference videos must add up to 2 to 15 seconds and reference audio to at most 15 seconds. Reference videos are billed for their own length too, so clips with video references cost more per second.

Parameters

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

NameType DefaultAllowed Description
promptrequired
Typestring
Text prompt that guides video generation.
image_urlsoptional images
Typeurl[] · image
≤ 9 items
Image references for video guidance, limited to 9 images and subject to a 12-file maximum across all modalities. Each image may be at most 30 MB and must use JPEG, PNG, or WebP. Use @Image1, @Image2, and subsequent numbered labels to identify these references in the prompt.
video_urlsoptional videos
Typeurl[] · video
≤ 3 items
Video references for generation, supplied as MP4 or MOV files and identified in the prompt by @Video1, @Video2, and subsequent numbered labels. Each must have a resolution from approximately 480p (640x640) to approximately 720p (834x1112). The set is limited to 3 videos totaling less than 50 MB, with an aggregate duration from 2 to 15 seconds.
audio_urlsoptional audios
Typeurl[] · audio
≤ 3 items
Audio references for video guidance require at least one accompanying image or video reference. Supply MP3 or WAV files of at most 15 MB each, with no more than 3 files and an aggregate duration capped at 15 seconds. Identify them in the prompt using @Audio1, @Audio2, and subsequent numbered labels.
resolutionoptional
Typeenum
Default720p
480p720p
Output resolution: 480p favors generation speed, while 720p offers a balanced choice.
durationoptional
Typeenum
Defaultauto
auto456789101112131415
Video length selection: `auto` delegates the choice to the model using the prompt, while an explicit duration must be from 4 to 15 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.
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-2.0/fast/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": 565,
    "usd": "0.565",
    "charged": 565,
    "refunded": 0
  },
  "input": {
    "prompt": "@Image1 The white sneaker spins slowly on a wet neon street, puddle splashes in slow motion, punchy beat",
    "images": [
      "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg"
    ],
    "duration": 5,
    "resolution": "480p"
  },
  "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
  },
  "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.

More models: Reference to Video

For AI agents: this page as Markdown is at https://doitong.com/developers/models/bytedance/seedance-2.0/fast/reference-to-video.md. All models and guides: https://doitong.com/developers/llms.txt