Seedance 2.5

Text-to-Video • ByteDance

bytedance/seedance-2.5

  • Third-party

ByteDance's next-generation video model with a unified multimodal reference-to-video architecture. Generates video from text, up to 30 reference images, 10 reference videos, and 10 reference audio clips — including audio-only input with no image or video required. Supports first/last-frame image-to-video, video editing, video extension, intelligent duration (including automatic selection), and adaptive aspect ratio.

Model Info
More information link ↗
Pricing <ul><li>Default (per second)$0.2312</li><li>@480p video input (per second)$0.4304</li><li>@720p video input (per second)$0.9676</li><li>@480p non-video input (per second)$0.1028</li><li>@720p non-video input (per second)$0.2312</li></ul>

Usage

const response = await env.AI.run(
  'bytedance/seedance-2.5',
  {
    prompt: 'A golden retriever running through a field of sunflowers on a sunny day',
    duration: 5,
    resolution: '720p',
  },
)
console.log(response)

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "bytedance/seedance-2.5",
  "input": {
    "prompt": "A golden retriever running through a field of sunflowers on a sunny day",
    "duration": 5,
    "resolution": "720p"
  }
}'

{
  "state": "Completed",
  "result": {
    "video": "https://examples.aig.cloudflare.com/bytedance/seedance-2.5/simple-video.mp4"
  },
  "gatewayMetadata": {
    "keySource": "Unified"
  }
}

Examples

<details>

<summary>Cinematic Wide Shot — Longer cinematic video with an explicit 16:9 aspect ratio</summary>

const response = await env.AI.run(
  'bytedance/seedance-2.5',
  {
    prompt:
      'A dramatic drone shot flying through misty mountain peaks at sunrise, cinematic lighting with volumetric fog',
    aspect_ratio: '16:9',
    duration: 12,
    resolution: '720p',
  },
)
console.log(response)

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "bytedance/seedance-2.5",
  "input": {
    "prompt": "A dramatic drone shot flying through misty mountain peaks at sunrise, cinematic lighting with volumetric fog",
    "aspect_ratio": "16:9",
    "duration": 12,
    "resolution": "720p"
  }
}'

{
  "state": "Completed",
  "result": {
    "video": "https://examples.aig.cloudflare.com/bytedance/seedance-2.5/cinematic-wide-shot.mp4"
  },
  "gatewayMetadata": {
    "keySource": "Unified"
  }
}

</details>

<details>

<summary>First and Last Frame — Generate a video that transitions between a given first-frame and last-frame image</summary>

const response = await env.AI.run(
  'bytedance/seedance-2.5',
  {
    image: 'https://ark-doc.tos-ap-southeast-1.bytepluses.com/doc_image/r2v_tea_pic1.jpg',
    last_frame_image: 'https://ark-doc.tos-ap-southeast-1.bytepluses.com/doc_image/r2v_tea_pic2.jpg',
    prompt: 'The character slowly turns to face the camera and smiles',
    duration: 5,
    resolution: '720p',
  },
)
console.log(response)

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "bytedance/seedance-2.5",
  "input": {
    "image": "https://ark-doc.tos-ap-southeast-1.bytepluses.com/doc_image/r2v_tea_pic1.jpg",
    "last_frame_image": "https://ark-doc.tos-ap-southeast-1.bytepluses.com/doc_image/r2v_tea_pic2.jpg",
    "prompt": "The character slowly turns to face the camera and smiles",
    "duration": 5,
    "resolution": "720p"
  }
}'

{
  "state": "Completed",
  "result": {
    "video": "https://examples.aig.cloudflare.com/bytedance/seedance-2.5/first-and-last-frame.mp4"
  },
  "gatewayMetadata": {
    "keySource": "Unified"
  }
}

</details>

<details>

<summary>Portrait Video with MOV Output — Vertical video for social media, encoded as mov for higher color fidelity</summary>

const response = await env.AI.run(
  'bytedance/seedance-2.5',
  {
    prompt: 'Abstract ink drops spreading through water, vivid colors mixing in slow motion',
    aspect_ratio: '9:16',
    duration: 5,
    resolution: '720p',
    output_format: 'mov',
  },
)
console.log(response)

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "bytedance/seedance-2.5",
  "input": {
    "prompt": "Abstract ink drops spreading through water, vivid colors mixing in slow motion",
    "aspect_ratio": "9:16",
    "duration": 5,
    "resolution": "720p",
    "output_format": "mov"
  }
}'

{
  "state": "Completed",
  "result": {
    "video": "https://examples.aig.cloudflare.com/bytedance/seedance-2.5/portrait-video-with-mov-output.mov"
  },
  "gatewayMetadata": {
    "keySource": "Unified"
  }
}

</details>

Parameters

prompt

stringmaxLength: 2000Text prompt describing the video to generate. Optional when at least one reference image, video, or audio clip is provided (Seedance 2.5 supports audio-only input).

image

stringFirst-frame reference image (HTTP(S) URL or base64 data URI) for image-to-video

last_frame_image

stringLast-frame reference image (HTTP(S) URL or base64 data URI). Requires a first-frame image to also be given.

▶reference_images[]

arraymaxItems: 30Reference images (0-30, HTTP(S) URLs or base64 data URIs) to guide multimodal video generation, editing, or extension.

▶reference_videos[]

arraymaxItems: 10Reference videos (0-10, HTTP(S) URLs or base64 data URIs) for style/motion guidance, video editing, or video extension. Total duration of all reference videos must not exceed 30 seconds.

▶reference_audios[]

arraymaxItems: 10Reference audio clips (0-10, HTTP(S) URLs or base64 data:audio/... URIs). Supports audio-only input (no image or video required). Total duration of all audio clips must not exceed 30 seconds.

▶duration

one ofrequired

resolution

stringrequireddefault: 720penum: 480p, 720pVideo resolution

aspect_ratio

stringrequireddefault: adaptiveenum: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptiveVideo aspect ratio. "adaptive" automatically matches the aspect ratio of the provided reference image or video when applicable. First/last-frame generation always uses "adaptive"; any supplied value is overridden.

fps

numberrequireddefault: 24const: 24Frame rate (frames per second)

camera_fixed

booleanrequireddefault: falseWhether to fix camera position. Not currently supported by the provider; has no effect.

generate_audio

booleanWhether to generate audio with the video

watermark

booleanrequireddefault: falseWhether to add a watermark to the output video

seed

integerminimum: -9007199254740991maximum: 9007199254740991Random seed. Passing this does not error, but reproducibility is not guaranteed and is not documented by the provider.

output_format

stringrequireddefault: mp4enum: mp4, movOutput video container format. "mp4" offers the best compatibility and smaller file size; "mov" preserves higher color fidelity for professional post-production workflows at the cost of a larger file.

use_virtual_avatar

booleanrequireddefault: falseRoute image reference inputs (image, reference_images, last_frame_image) through ByteDance's trusted virtual avatar asset library before generation. Intended for AI-generated/virtual character avatars that would otherwise be blocked by face or deepfake detection

video

stringformat: uriURL to the generated video

API Schemas (Raw)

Input Open Download

Output Open Download

Was this helpful?

YesNo

On this page

Seedance 2.5 - 图1Docs

{"@context":"https://schema.org","@type":"TechArticle","@id":"https://developers.cloudflare.com/ai/models/bytedance/seedance-2.5/#page","headline":"Seedance 2.5","description":"ByteDance's next-generation video model with a unified multimodal reference-to-video architecture. Generates video from text, up to 30 reference images, 10 reference videos, and 10 reference audio clips — including audio-only input with no image or video required. Supports first/last-frame image-to-video, video editing, video extension, intelligent duration (including automatic selection), and adaptive aspect ratio.","url":"https://developers.cloudflare.com/ai/models/bytedance/seedance-2.5/","inLanguage":"en","image":"https://developers.cloudflare.com/og-docs.png","publisher":{"@type":"Organization","name":"Cloudflare","description":"One platform for your apps, agents, and workforce. Build, secure, and scale without managing infrastructure","url":"https://www.cloudflare.com/","sameAs":["https://github.com/cloudflare","https://www.linkedin.com/company/cloudflare","https://x.com/cloudflare"],"logo":{"@type":"ImageObject","url":"https://developers.cloudflare.com/logo.svg"},"address":{"@type":"PostalAddress","streetAddress":"101 Townsend St","addressLocality":"San Francisco","addressRegion":"CA","postalCode":"94107","addressCountry":"US"},"contactPoint":[{"@type":"ContactPoint","contactType":"Customer Support","url":"https://support.cloudflare.com/","availableLanguage":["English"]},{"@type":"ContactPoint","contactType":"Sales","url":"https://www.cloudflare.com/contact/","availableLanguage":["English"]}]},"isPartOf":{"@type":"WebSite","@id":"https://developers.cloudflare.com/#website","name":"Cloudflare Docs","url":"https://developers.cloudflare.com/"}}

description: Seedream 4.0 is ByteDance's image creation model that combines text-to-image generation and image editing into a single architecture, offering fast, high-resolution output up to 4K. title: Seedream 4.0 image: https://developers.cloudflare.com/og-docs.png

Skip to content

Documentation Index
Fetch the complete documentation index at: https://developers.cloudflare.com/llms.txt
Use this file to discover all available pages before exploring further.

ByteDance logo