MEDIA API

Dreamina Seedance 2.0 Fast

A new-generation professional-grade multimodal video creation model, supports video generation with multimodal reference inputs including images, videos and audio. It also features video editing and extension capabilities.Seedance-2.0-fast is a new-generation multimodal video creation model, inheriting the core functions and advantages of Seedance-2.0, with faster speed.

提供商BytePlus

dreamina-seedance-2-0-fast-260128
Text to VideoImage to VideoVideo to Video

API 价格

USD / 1M completion tokens; varies by resolution and video input

费用以实际用量和模型的计费规则结算。媒体任务可能涉及输出数量、视频时长或上游实际费用。

Input Schema

以下为请求体 params 对象内的参数说明。

Input Schema
nametyperequireddescription
modelstringtrueModel ID
contentobject[]trueInput content list. References provided to the model for video generation, supporting text, image, audio, video, and sample task ID.
content.typestringtrueContent type. For text input set to text; for image input set to image_url; for video input set to video_url; for audio input set to audio_url; for draft task input set to draft_task.
content.textstringtrueText prompt input to the model, describing the expected generated video.
content.image_urlobjecttrueThe input image object for the model.
content.image_url.urlstringtrueImage source. Accepts image URL, Base64-encoded image, or asset ID.
content.rolestringconditionalRole/purpose of the image, video, or audio. Image roles include first_frame, last_frame, and reference_image; video role is reference_video; audio role is reference_audio.
content.video_urlobjecttrueThe video object provided to the model.
content.video_url.urlstringtrueVideo source. Accepts video URL or asset ID.
content.audio_urlobjecttrueAudio object provided to the model.
content.audio_url.urlstringtrueAudio source. Accepts URL, Base64-encoded string, or asset ID.
content.draft_taskobjecttrueDraft task input to the model.
content.draft_task.idstringtrueDraft task ID.
omni_reference_task_typestringfalseTask type hint. Default value: auto.
resolutionstringfalseVideo resolution.
ratiostringfalseVideo aspect ratio.
durationintegerfalseVideo duration.
framesintegerfalseVideo frame count.
generate_audiobooleanfalseControls whether the generated video includes sound synchronized with the footage. Default: true.
watermarkbooleanfalseVideo watermark. Default value: false.
output_formatstringfalseOutput format. Default value: mp4.
seedintegerfalseRandom seed used to control the randomness of generated content. Default value: -1. Value range: [-1, 2147483647].
camera_fixedbooleanfalseFix camera. Default value: false.
return_last_framebooleanfalseReturn last frame. Default value: false.
draftbooleanfalseDraft mode. Default: false.
service_tierstringfalseService tier. Default value: default. Valid values include default and flex.
callback_urlstringfalseCallback URL.
execution_expires_afterintegerfalseTask expiration threshold. Default value: 172800.
priorityintegerfalseExecution priority. Default: 0.
safety_identifierstringfalseEnd-user identifier.

Output Schema

Output Schema
nametypedescription
idstringVideo generation task ID. Stored for only 7 days from the created-at timestamp. When "draft": true is set, it is the draft video task ID; when "draft": false is set, it is the normal video task ID. The task creation API is asynchronous; use this ID to query the video generation task status.

调用方式

在控制台创建密钥,通过服务端调用 API,使用 apiKey 请求头进行认证。

POST https://restapi.scalingtensor.com/api/media/generate

curl --request POST 'https://restapi.scalingtensor.com/api/media/generate' \
  --header 'apiKey: YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data-raw '{
  "model": "dreamina-seedance-2-0-fast-260128",
  "params": {
    "ratio": "16:9",
    "content": [
      {
        "text": "Use the first-person POV framing from Video 1 throughout, and use Audio 1 as the background music throughout. First-person POV fruit tea promotional ad, Seedance brand limited-edition apple fruit tea; opening frame is Image 1, your hand picks a dew-covered Aksu red apple, a light, crisp apple tapping sound; 2–4 seconds: fast cuts, your hand drops apple chunks into a shaker, adds ice and tea base, shakes forcefully, ice clinking and shaking sounds sync with upbeat rhythmic beats, background audio: {Fresh-cut, shaken fresh}; 4–6 seconds: first-person close-up of the finished drink, layered fruit tea is poured into a clear cup, your hand gently squeezes milk foam to spread across the top, a pink brand sticker is applied to the cup, the camera moves closer to show the layered textures of the foam and fruit tea; 6–8 seconds: first-person hand-held toast shot, you raise the fruit tea from Image 2 toward the camera (simulating handing it to the viewer), the cup label is clearly visible, background audio {Take a sip of fresh refreshment}, the final frame freezes on Image 2. All background voice audio uses a female voice.",
        "type": "text"
      },
      {
        "role": "reference_image",
        "type": "image_url",
        "image_url": {
          "url": "https://ark-doc.tos-ap-southeast-1.bytepluses.com/doc_image/r2v_tea_pic1.jpg"
        }
      },
      {
        "role": "reference_image",
        "type": "image_url",
        "image_url": {
          "url": "https://ark-doc.tos-ap-southeast-1.bytepluses.com/doc_image/r2v_tea_pic2.jpg"
        }
      },
      {
        "role": "reference_video",
        "type": "video_url",
        "video_url": {
          "url": "https://ark-doc.tos-ap-southeast-1.bytepluses.com/doc_video/r2v_tea_video1.mp4"
        }
      },
      {
        "role": "reference_audio",
        "type": "audio_url",
        "audio_url": {
          "url": "https://ark-doc.tos-ap-southeast-1.bytepluses.com/doc_audio/r2v_tea_audio1.mp3"
        }
      }
    ],
    "duration": 11,
    "watermark": false,
    "generate_audio": true
  }
}'

将 YOUR_API_KEY 替换为密钥;JavaScript 示例从服务端环境变量 SCALINGTENSOR_API_KEY 读取密钥。提交成功后保存 data.jobId,通过 GET /api/media/result?jobId=... 查询结果,并携带相同的 apiKey 请求头。code 为 0 表示业务请求成功。

浏览全部模型与价格 · Markdown API reference