跳到主要内容

ByteDanceVideo model检查中

Seedance 2.0 API

模型 IDseedance-2-0-global-text-to-video

ByteDance's multimodal Seedance 2.0 video model, with text, image and reference-based variants in the Hermes catalog.

  • Reference to video
  • 图生视频
  • 文生视频
  • Up to 9 input images
  • Up to 15 seconds
  • 1080p, 2K or 4K output
  • 声音

在 Playground 中运行 Seedance 2.0

The form is the request body: every field shows its key. Sign in to run it; a run is billed like an API task.

参数

模型
model

Seedance 2.0Global text to videoseedance-2-0-global-text-to-video

必填
input.prompt

Text prompt for video generation. ≤ 20480 chars

input.resolution

Video resolution. Includes native resolutions directly output by the model (480p, 720p, native1080p), and upscaled resolutions based on native 720p generation (1080p, 2k, 4k).

input.duration

Video duration (seconds).

常用参数
input.ratio

Video aspect ratio.

高级参数 (3)
input.generateAudio

Generate audio for the video.

input.returnLastFrame

Return the last frame image of the generated video.

input.seed

Seed integer, used to control the randomness of generated content. -1–2147483647

预估费用
正在加载价格…

任务接收时预留额度,仅成功后扣费。失败任务释放预留额度;结果未确认时会保留额度,直到核实。

请求预览

{"model": "seedance-2-0-global-text-to-video","input": {"resolution": "720p","duration": "5","generateAudio": true,"ratio": "adaptive","returnLastFrame": false,"seed": -1}}

网页 Playground 使用你的登录会话发送此请求体。在代码中请使用 API Key 发送相同内容。

结果

运行请求后,结果会显示在这里,并附上状态和费用。

Seedance 2.0 价格

各可用版本和规格的价格以美元显示,计费单位随费率注明;只有找到可匹配的官方标价时才显示参考价格。

正在加载价格…
  • Charged only on success仅对成功任务扣费。失败任务释放预留额度;结果尚未确认的任务会保留额度,直到结果核实。
  • Safe retries使用相同幂等密钥重试不会重复扣费。
  • Price changes发送 expectedPriceMicros:若展示后价格发生变化,任务会以 PRICE_CHANGED 被拒绝。

对比 Seedance 2.0 各版本

每个变体都有独立的模型 ID 和输入参数。请先选择任务和版本;变体存在差异时会显示额外字段。

  • Global mini multimodal video

    seedance-2-0-global-mini-multimodal-video

    Reference to video; 文本, 图像, 视频, audio; 4–15 s; 480p, 720p, 1080p, 2K, 4K; 16:9, 4:3, 1:1, 3:4, 9:16, 21:9

  • Global mini image to video

    seedance-2-0-global-mini-image-to-video

    图生视频; 文本, 图像; 4–15 s; 480p, 720p, 1080p, 2K, 4K; 16:9, 4:3, 1:1, 3:4, 9:16, 21:9

  • Global mini text to video默认值

    seedance-2-0-global-mini-text-to-video

    文生视频; 文本; 4–15 s; 480p, 720p, 1080p, 2K, 4K; 16:9, 4:3, 1:1, 3:4, 9:16, 21:9

  • Global fast multimodal video

    seedance-2-0-global-fast-multimodal-video

    Reference to video; 文本, 图像, 视频, audio; 4–15 s; 480p, 720p, 1080p, 2K, 4K; 16:9, 4:3, 1:1, 3:4, 9:16, 21:9

  • Global fast image to video

    seedance-2-0-global-fast-image-to-video

    图生视频; 文本, 图像; 4–15 s; 480p, 720p, 1080p, 2K, 4K; 16:9, 4:3, 1:1, 3:4, 9:16, 21:9

  • Global fast text to video

    seedance-2-0-global-fast-text-to-video

    文生视频; 文本; 4–15 s; 480p, 720p, 1080p, 2K, 4K; 16:9, 4:3, 1:1, 3:4, 9:16, 21:9

  • Global multimodal video

    seedance-2-0-global-multimodal-video

    Reference to video; 文本, 图像, 视频, audio; 4–15 s; 480p, 720p, Native 1080p, Native 4K, 1080p, 2K, 4K; 16:9, 4:3, 1:1, 3:4, 9:16, 21:9

  • Global image to video

    seedance-2-0-global-image-to-video

    图生视频; 文本, 图像; 4–15 s; 480p, 720p, Native 1080p, Native 4K, 1080p, 2K, 4K; 16:9, 4:3, 1:1, 3:4, 9:16, 21:9

  • Global text to video

    seedance-2-0-global-text-to-video

    文生视频; 文本; 4–15 s; 480p, 720p, Native 1080p, Native 4K, 1080p, 2K, 4K; 16:9, 4:3, 1:1, 3:4, 9:16, 21:9

Seedance 2.0 能做什么

ByteDance describes Seedance 2.0 as a video model with joint audio-video generation and multimodal reference inputs. Its examples use reference media to guide composition, motion, camera work and sound. Those are manufacturer-described capabilities; the fields and limits of an individual channel can differ.

The Hermes catalog lists nine variants: standard, Fast and Mini tiers, each with text-to-video, image-to-video and multimodal-reference modes. The multimodal schemas list up to nine reference images, three videos and three audio files in one request.

The schemas list resolution options from 480p to 4K and duration from 4 to 15 seconds, or -1 for automatic selection. They describe 1080p, 2K and 4K options as upscaled from 720p; the standard tier also lists native 1080p. The generateAudio field controls audio. Check the selected variant's current status and pricing before making a request.

能力

  • Up to 15 seconds

    Choose a length from 4 to 15 seconds.

    duration

    Every variant

  • Start and end frames

    Set the first frame and, optionally, the last frame the clip moves to.

    firstFrameUrllastFrameUrl

    版本: Global mini image to video, Global fast image to video, Global image to video

  • 声音

    Generate audio together with the video.

    generateAudio

    Every variant

  • 1080p, 2K or 4K output

    Pick the output resolution: 480p, 720p, 1080p, 2K or 4K.

    resolution

    Every variant

  • 6 aspect ratios

    16:9, 4:3, 1:1, 3:4, 9:16 or 21:9.

    ratio

    Every variant

  • Up to 9 input images

    Send up to 9 images in one request as HTTPS URLs or uploaded media references.

    imageUrls

    版本: Global mini multimodal video, Global fast multimodal video, Global multimodal video

  • Video input

    Accepts a source video as input.

    videoUrls

    版本: Global mini multimodal video, Global fast multimodal video, Global multimodal video

  • Audio input

    Accepts reference audio as input.

    audioUrls

    版本: Global mini multimodal video, Global fast multimodal video, Global multimodal video

  • 随机种子

    Accepts a seed value.

    seed

    Every variant

使用场景

  1. Consistent characters and products

    Pass reference images, clips and audio to the multimodal variants so the result follows them.

  2. First and last frame control

    The image to video variants take firstFrameUrl and an optional lastFrameUrl.

  3. Chained clips

    Set returnLastFrame to get the final frame back and use it as the first frame of the next request.

用代码调用 Seedance 2.0

Every image, video and music model uses the same asynchronous job API: submit a task, then poll for the result.

  1. 1

    创建 API Key

    In the dashboard, with the jobs:create and jobs:read scopes. API 密钥
  2. 2

    提交任务

    POST /api/v1/jobs with the model ID and an input object. The response is 202 with a task ID.
  3. 3

    Poll for the result

    GET /api/v1/jobs/{id} until the status is succeeded, then download the output URLs.

最小请求

Required fields only, generated from the schema of Global text to video. Set HERMES_API_KEY in your environment.

模型 ID
seedance-2-0-global-text-to-video
端点
https://api.hermes-ai.net/api/v1/jobs
Full task API reference
# 1. Submit the task (asynchronous; returns 202 with a task id)
curl -X POST https://api.hermes-ai.net/api/v1/jobs \
  -H "Authorization: Bearer $HERMES_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "seedance-2-0-global-text-to-video",
  "input": {
    "prompt": "A lighthouse on a rocky coast at sunrise, soft light",
    "resolution": "720p",
    "duration": "5"
  }
}'

# 2. Poll until status is succeeded, failed or reconciliation_required
curl https://api.hermes-ai.net/api/v1/jobs/TASK_ID \
  -H "Authorization: Bearer $HERMES_API_KEY"

输入参数

Fields of Global text to video (seedance-2-0-global-text-to-video). 未知字段会被拒绝并返回 INVALID_MODEL_INPUT。

字段类型必填默认值可选值与约束
prompt
string必填—

Text prompt for video generation.

≤ 20480 chars

resolution
string必填"720p"

Video resolution. Includes native resolutions directly output by the model (480p, 720p, native1080p), and upscaled resolutions based on native 720p generation (1080p, 2k, 4k).

可选值: "480p", "720p", "native1080p", "native4k", "1080p", "2k", "4k"

duration
string必填"5"

Video duration (seconds).

可选值: "-1", "4", "5", "6", "7", "8", "9", "10", "11", "12", "13", "14", "15"

generateAudio
boolean可选true

Generate audio for the video.

ratio
string可选"adaptive"

Video aspect ratio.

可选值: "adaptive", "16:9", "4:3", "1:1", "3:4", "9:16", "21:9"

returnLastFrame
boolean可选false

Return the last frame image of the generated video.

seed
integer可选-1

Seed integer, used to control the randomness of generated content.

-1–2147483647

Headers, response, task statuses and errors
请求头值说明
AuthorizationBearer <API key>也可以通过 x-api-key 发送密钥。
Content-Typeapplication/json
Idempotency-Key<unique string ≤128>必填。仅在重试完全相同的请求时复用。
字段类型说明
idstringHermes AI 任务 ID,用于轮询。
modelstring模型 slug。
statusstring参见任务状态。
errorCodestring | null任务失败或需要核对时设置。
priceMicrosinteger接收时锁定的报价,美元微单位。
currency"USD"
createdAt / updatedAtstringISO 8601 时间戳。
assets[]array{ id, type, url?, text? }。url 为同源 /api/v1/results/<uuid> 链接。
replayedboolean仅提交时返回。幂等重试命中时为 true。
状态终态含义
queued否已接收,等待执行。
submitting否正在提交给模型提供方。
running否模型生成中。
succeeded是已完成,结果位于 assets。
failed是未产生结果,预留额度已释放。
reconciliation_required是结果正在核实。请保留任务 ID,不要自动重新提交。
HTTP代码含义与处理方式
401AUTH_REQUIRED缺少或无效的 API Key 或会话。
403INSUFFICIENT_SCOPEAPI Key 缺少此端点所需的权限。
403PERMISSION_DENIED此凭据无权执行该操作。
429API_KEY_RATE_LIMITED已达到 API Key 的频率限制,请遵循 Retry-After。
429API_KEY_USAGE_EXCEEDEDAPI Key 已达到使用上限,请创建新密钥。
400INVALID_REQUEST请求体不是 JSON 对象,或缺少必需值。
400INVALID_IDEMPOTENCY_KEYIdempotency-Key 必须是 1–128 个可打印 ASCII 字符。
400INVALID_MODEL_INPUTinput 与模型 schema 不匹配(未知字段、缺少必填字段或值无效)。
400 / 413INPUT_TOO_LARGE请求体超过 256 KB。请先上传媒体并发送媒体引用。
404REQUEST_NOT_FOUNDNo chat request with this ID belongs to your account.
404MODEL_NOT_FOUND没有此 slug 对应的模型。
404JOB_NOT_FOUND你的账户中没有此 ID 的任务。
409IDEMPOTENCY_CONFLICT此 Idempotency-Key 已用于不同的输入。新请求请使用新密钥。
409PRICE_CHANGED价格与 expectedPriceMicros 不一致。请重新获取价格并确认。
409MODEL_PRICE_UNAVAILABLE此模型尚未配置价格,暂不可运行。
409PAYMENT_REVIEW_REQUIRED退款后余额不足。请联系支持或补足余额后再提交任务。
409INSUFFICIENT_CREDITS可用额度不足以支付此任务。
429RATE_LIMITED每分钟提交次数过多,请稍后重试。
429EXPORT_RATE_LIMITED本分钟内导出 CSV 次数过多,请按 Retry-After 等待后重试。
429CONCURRENCY_LIMITED未完成任务过多,请等待任务完成。
503EXECUTION_UNAVAILABLE此模型当前未配置执行能力。
429UPSTREAM_RATE_LIMITEDThe model provider is rate limiting chat requests. Retry with backoff; nothing was charged.
502UPSTREAM_ERRORThe model provider failed the chat request. Nothing was charged; retry later.
503PLATFORM_BUDGET_EXCEEDED此模型暂时不可用,请稍后重试。
503EXECUTION_TEMPORARILY_UNAVAILABLE执行暂时不可用,请使用相同的 Idempotency-Key 重试。
503AUTH_UNAVAILABLE身份验证暂时不可用,请稍后重试。
503API_UNAVAILABLEAPI 暂时不可用,请稍后重试。

Seedance 2.0 API 常见问题

Answers built from the model's schema and the Hermes AI API contract.

What does a duration of -1 mean?

The model chooses the length. Video billed by duration is then charged by the measured output, as the pricing table on this page explains.

Are 2K and 4K native?

No. According to the schema they are generated at 720p and upscaled; 480p and 720p, and native1080p on the standard tier, are output directly.

What can the Seedance 2.0 API do?

ByteDance 的 Seedance 2.0 支持参考生视频, 图生视频 和 文生视频。目录列有9 variants, each,每个变体都有自己的模型 ID 和输入参数。提交请求前请先确认当前可用状态。

Which durations, resolutions and aspect ratios does Seedance 2.0 support?

Across its variants, Seedance 2.0 supports durations from 4 to 15 seconds, 480p, 720p, 1080p, 2K, 4K, Native 1080p 和 Native 4K resolution 和 aspect ratios 16:9, 4:3, 1:1, 3:4, 9:16 和 21:9. Each variant accepts its own subset; the variants table on this page lists them.

What input does Seedance 2.0 accept?

A text prompt of up to 20,480 characters, plus 图像, 视频 或 audio input (up to 9 images per request). Media fields take a public HTTPS URL or a media:<uuid> reference returned by POST /api/v1/media, so local files can be uploaded first. 未知字段会被拒绝并返回 INVALID_MODEL_INPUT。

How is Seedance 2.0 priced and billed?

You pay per successful task from prepaid credits, with no subscription. The price depends on the variant and the specification you choose, such as resolution or duration; see the pricing table on this page or the pricing page. Credits are reserved when a task is accepted and charged only when it succeeds; a failed task returns the reservation to your balance.

Which Seedance 2.0 variant should I choose?

For reference to video, Global mini multimodal video, Global fast multimodal video 和 Global multimodal video take the same input fields and differ in tier and price; for 图生视频, Global mini image to video, Global fast image to video 和 Global image to video take the same input fields and differ in tier and price; for 文生视频, Global mini text to video, Global fast text to video 和 Global text to video take the same input fields and differ in tier and price. Pick the task first, then compare the tiers in the variants table.

How do I call the Seedance 2.0 API from code?

Send POST https://api.hermes-ai.net/api/v1/jobs with the variant's model ID and an input object, then poll GET /api/v1/jobs/{id} until the status is succeeded or failed. The API section has cURL, JavaScript and Python examples generated from the schema.

Can I try Seedance 2.0 without writing code?

Yes. Sign in and use the playground on this page: it sends the same request as the API with your session and charges the same price. Code needs an API key from the dashboard.

What happens when a task fails or I hit a rate limit?

A failed task is not charged and its reserved credits are returned. Too many submissions per minute return 429 RATE_LIMITED, and too many unfinished tasks return 429 CONCURRENCY_LIMITED; retry later or wait for a task to finish.