How to Generate Videos with the Seedance API: A Practical Builder Guide

How to Generate Videos with the Seedance API: A Practical Builder Guide

When you are building a product that needs short generated video clips, the hard part is usually not the prompt itself. It is turning a prompt, a reference image, or multimodal inputs into a repeatable API workflow that your app can validate, retry, and observe.

The Seedance Videos API on Ace Data Cloud follows a typed job pattern: send structured content to POST https://api.acedata.cloud/seedance/videos, choose a model, describe the output shape, and read the returned task result.

What you can do

  • Text to video: send a content item with type: "text" and a prompt.
  • Image to video: send an image_url content item, then describe motion with text.
  • First and last frame control: mark images with role: "first_frame" and role: "last_frame".
  • Multimodal reference: Seedance 2.0 models support reference_image, reference_audio, and reference_video.
  • Editing and extension: doubao-seedance-2-5-260628 supports omni_reference_task_type values such as auto, reference, edit, and extend.

How it works

A basic request uses JSON headers: accept: application/json, authorization: Bearer {token}, and content-type: application/json. The main body fields are model, content, resolution, ratio, and duration.

Useful models include doubao-seedance-2-0-fast-260128, doubao-seedance-2-0-260128, doubao-seedance-2-0-mini-260615, and doubao-seedance-2-5-260628. The resolution field can be 480p, 720p, 1080p, or, where supported, 4k. The ratio field can be 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, or adaptive.

Duration is model dependent. Seedance 2.0 supports 4 to 15 seconds, while Seedance 2.5 supports 4 to 30 seconds. Some 1.5 and 2.x workflows also support -1 for automatic length.

Start with text-to-video

Here is the smallest useful request: one text prompt, a fast Seedance 2.0 model, and explicit output controls.

curl -X POST 'https://api.acedata.cloud/seedance/videos' \
  -H 'authorization: Bearer {token}' \
  -H 'accept: application/json' \
  -H 'content-type: application/json' \
  -d '{
    "content": [{"type":"text","text":"A white ceramic coffee mug on a glossy marble countertop with soft morning window light. The camera slowly orbits 360 degrees around the mug, steam gently rising."}],
    "model": "doubao-seedance-2-0-fast-260128",
    "resolution": "720p",
    "ratio": "16:9",
    "duration": 5
  }'

A successful response includes success, task_id, trace_id, and data. Inside data, the API can return status, model, duration, resolution, ratio, and video_url.

{
  "success": true,
  "task_id": "9777f36b-4f44-47ff-962d-45cd2f7aeaa8",
  "trace_id": "ce5da2ca-6695-4459-9d2c-2ef9f86db752",
  "data": {
    "status": "succeeded",
    "model": "doubao-seedance-2-0-fast-260128",
    "duration": 5,
    "resolution": "720p",
    "ratio": "16:9",
    "video_url": "https://platform2.cdn.acedata.cloud/seedance/example.mp4"
  }
}

Prefer structured fields over inline flags

The docs also describe inline prompt parameters such as --rs, --rt, --dur, --seed, --cf, and --wm. They map to resolution, ratio, duration, seed, camerafixed, and watermark. For product code, top-level JSON fields are easier to validate and debug.

Add references when consistency matters

For image-to-video, image_url must be an object, not a string:

{
  "type": "image_url",
  "image_url": {"url": "https://example.com/reference.png"}
}

If you use first and last frame control, use first_frame and last_frame. For Seedance 2.0 multimodal references, use reference_image, reference_audio, or reference_video. The docs note that first/last-frame workflows and full-modal reference workflows should not be mixed in the same request.

Seedance 2.0 supports up to 9 image references, up to 3 audio references, and up to 3 video references. Reference audio supports wav and mp3, each item 2 to 15 seconds, total duration not exceeding 15 seconds, and a single item not exceeding 15 MB. Reference video supports mp4 and mov, each item 2 to 15 seconds and total duration not exceeding 15 seconds.

Use Seedance 2.5 for editing and extension

Seedance 2.5 adds omni_reference_task_type. For editing, the request must include a reference_video, use ratio: "adaptive", and use duration: -1. For extension, use ratio: "adaptive" and choose duration from 4 to 30, or -1.

{
  "model": "doubao-seedance-2-5-260628",
  "content": [
    {"type":"text","text":"Replace the sky with a warm golden evening while preserving the subject and camera motion."},
    {"type":"video_url","role":"reference_video","video_url":{"url":"https://cdn.acedata.cloud/input.mp4"}}
  ],
  "resolution": "720p",
  "ratio": "adaptive",
  "duration": -1,
  "omni_reference_task_type": "edit",
  "output_format": "mov"
}

Production notes

If you build this into a product, validate content shapes before sending, store task_id and trace_id for support, and use safety_identifier as a stable anonymous user identifier instead of personal data. For async systems, callback_url can return a task immediately and post results to your service when generation completes.

The Seedance API is most useful when treated as a typed media job interface, not a one-off prompt box. Start with text-to-video or image-to-video, then add reference roles and Seedance 2.5 editing only when your workflow needs them.

Read the full reference in the Seedance Videos API integration guide.

Comments

Post a Comment

Popular posts from this blog

Artistic QR Code API Integration Guidance

Image
Artistic QR code is an innovative technological product that combines QR codes with beautiful background images, creating practical and visually appealing works. They not only possess the functionality of traditional QR codes, allowing quick scanning and recognition by smart devices, but also incorporate artistic elements to enhance visual appeal and brand recognition. Some artistic QR codes are even generated by artificial intelligence, fully leveraging modern technology to demonstrate unparalleled innovation and uniqueness. This makes artistic QR codes widely applicable in areas such as brand marketing and advertising. In simple terms, artistic QR codes are the perfect combination of QR code scanning and artistic aesthetics. They not only provide the function of information transmission, but also enhance the user's visual experience, making each scan a delightful artistic enjoyment. Overview of Artworks Let's take a look at a few QR code works: How are they? These are ar...
Read more

How to Configure Claude Code with CC Switch and Ace Data Cloud

Image
If you use Claude Code across a terminal, VS Code, or remote development setup, the awkward part is often not the model itself but the configuration: where should requests go, where should the token live, and how do you switch providers without editing files by hand? This guide walks through a practical setup using CC Switch as the graphical configuration manager and Ace Data Cloud as the Anthropic-compatible base URL. The goal is simple: configure Claude Code once, verify the active endpoint, and keep the setup easy to change later. What you can do With the setup described in the Ace Data Cloud documentation, you can: Manage Claude Code provider configuration through a desktop UI instead of manually editing settings.json . Store an Ace Data Cloud provider with ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN . Switch the active Claude Code provider from CC Switch without rewriting your configuration every time. Use the same provider configuration from the terminal an...
Read more

How to Build a Server-Side Image Editing Workflow with GPT-Image-2

Image
If your product needs image editing, the hard part is rarely the model call itself. The real challenge is building a reliable workflow around user images, reference assets, predictable output sizes, and slow-running jobs without forcing every file through a manual upload step. This guide walks through a practical server-side workflow using the OpenAI Images Edits API on Ace Data Cloud. The focus is gpt-image-2 , because the documented editing flow supports direct image URLs, base64 input, multiple reference images, high-resolution output through size , and asynchronous callbacks. What you can do The edits endpoint is designed for turning one or more input images plus an instruction into a modified output image. In practical terms, you can use it to: Convert an existing infographic or poster into a different visual theme while preserving its layout. Change a product, shelf, room, or object style while keeping the original arrangement stable. Pass image URLs directly f...
Read more