Back to Details

bytedance-seedance-2-0

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

ByteDance Seedance 2.0 (Fast)

ByteDance Seedance 2.0（Fast版本）

ByteDance Seedance 2.0 on the EachLabs Predictions API. Seedance 2.0 generates cinematic video with native synchronized audio (sound effects, ambient sound, lip-synced speech), realistic physics, and director-level camera control.
Two model slugs:
SlugCategoryUse
bytedance-seedance-2-0-text-to-video-fast
Text to VideoGenerate a video from a prompt
bytedance-seedance-2-0-image-to-video-fast
Image to VideoAnimate a starting frame (optionally to an end frame)
The "Fast" tier prioritizes rapid turnaround for high-throughput pipelines while keeping the family's character consistency and physics.
基于EachLabs预测API的ByteDance Seedance 2.0。Seedance 2.0可生成带有原生同步音频（音效、环境音、唇形同步语音）、逼真物理效果和导演级镜头控制的电影级视频。
两种模型标识：
标识类型适用场景
bytedance-seedance-2-0-text-to-video-fast
文本转视频根据提示词生成视频
bytedance-seedance-2-0-image-to-video-fast
图片转视频将起始帧动画化（可选生成至结束帧）
“Fast”版本在保持该系列模型角色一致性和物理效果的同时，优先保障高吞吐量流水线的快速响应。

When to use

适用场景

  • User asks for "Seedance 2.0", "ByteDance video", or wants a Seedance-style look.
  • Native audio required in the same pass (dialogue, SFX, ambience) — no separate TTS/lipsync step.
  • Cinematic motion, realistic physics, or director-level camera language ("slow push in", "rack focus").
  • Durations of 4–15 seconds at 480p or 720p.
  • Image-to-video with an end frame to control where the clip lands.
For a wider video-model comparison (Veo, Kling, Sora, Pixverse, Hailuo, etc.) see 
eachlabs-video-generation
.
  • 用户要求使用“Seedance 2.0”、“ByteDance视频”，或想要Seedance风格的视频效果。
  • 需要原生音频同步生成（对话、音效、环境音）——无需单独的文本转语音/唇形同步步骤。
  • 需要电影级运镜、逼真物理效果，或导演级镜头语言（如“缓慢推近”、“焦点切换”）。
  • 时长4-15秒，分辨率为480p或720p的视频。
  • 需要通过结束帧控制片段最终画面的图片转视频需求。
如需对比更多视频生成模型（Veo、Kling、Sora、Pixverse、Hailuo等），请查看
eachlabs-video-generation
。

Authentication

身份验证

Header: X-API-Key: <your-api-key>
Set the 
EACHLABS_API_KEY
environment variable. Get your key at eachlabs.ai/dashboard/api-keys.
请求头：X-API-Key: <your-api-key>
设置
EACHLABS_API_KEY
环境变量。可前往eachlabs.ai/dashboard/api-keys获取密钥。

Prediction Flow

预测流程

  1. (Recommended) Check schema — 
    GET https://api.eachlabs.ai/v1/model?slug=bytedance-seedance-2-0-text-to-video-fast
    (or the i2v slug).
  2. POST 
    https://api.eachlabs.ai/v1/prediction
    with 
    model
    , 
    version: "0.0.1"
    , and 
    input
    .
  3. Poll 
    GET https://api.eachlabs.ai/v1/prediction/{id}
    until 
    status
    is 
    "success"
    or 
    "error"
    , or use a webhook.
  4. Extract the video URL from 
    output
    (string).
  1. （推荐）检查 schema — 调用
    GET https://api.eachlabs.ai/v1/model?slug=bytedance-seedance-2-0-text-to-video-fast
    （或图片转视频模型的标识）。
  2. POST请求 
    https://api.eachlabs.ai/v1/prediction
    ，携带
    model
    、
    version: "0.0.1"
    和
    input
    参数。
  3. 轮询 
    GET https://api.eachlabs.ai/v1/prediction/{id}
    ，直到
    status
    变为
    "success"
    或
    "error"
    ，或使用webhook接收结果。
  4. 提取结果 从
    output
    字段（字符串类型）中获取视频URL。

Quick Start — Text to Video

快速开始 — 文本转视频

bash
curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "bytedance-seedance-2-0-text-to-video-fast",
    "version": "0.0.1",
    "input": {
      "prompt": "Cinematic slow push-in on a lone astronaut standing at the edge of a Martian canyon at dusk, dust drifting across their boots, distant wind, subtle helmet reflections",
      "resolution": "720p",
      "duration": "6",
      "aspect_ratio": "16:9",
      "generate_audio": true
    }
  }'
Typical processing time: ~120 seconds.
bash
curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "bytedance-seedance-2-0-text-to-video-fast",
    "version": "0.0.1",
    "input": {
      "prompt": "Cinematic slow push-in on a lone astronaut standing at the edge of a Martian canyon at dusk, dust drifting across their boots, distant wind, subtle helmet reflections",
      "resolution": "720p",
      "duration": "6",
      "aspect_ratio": "16:9",
      "generate_audio": true
    }
  }'
典型处理时间：约120秒。

Quick Start — Image to Video

快速开始 — 图片转视频

bash
curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "bytedance-seedance-2-0-image-to-video-fast",
    "version": "0.0.1",
    "input": {
      "prompt": "Camera slowly pushes from wide to medium close-up as the lion roars at golden hour. Warm amber light rakes across the mane. Narrator (weathered British male, 50s): \"He has ruled this land for seven years.\"",
      "image_url": "https://your-cdn.example.com/lion.jpg",
      "resolution": "720p",
      "duration": "8",
      "aspect_ratio": "16:9",
      "generate_audio": true
    }
  }'
Typical processing time: ~150 seconds.
bash
curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "bytedance-seedance-2-0-image-to-video-fast",
    "version": "0.0.1",
    "input": {
      "prompt": "Camera slowly pushes from wide to medium close-up as the lion roars at golden hour. Warm amber light rakes across the mane. Narrator (weathered British male, 50s): \"He has ruled this land for seven years.\"",
      "image_url": "https://your-cdn.example.com/lion.jpg",
      "resolution": "720p",
      "duration": "8",
      "aspect_ratio": "16:9",
      "generate_audio": true
    }
  }'
典型处理时间：约150秒。

Start-to-end transition

起始帧到结束帧过渡

Pass 
end_image_url
to lock the final frame and let the model interpolate motion between the two:
json
{
  "model": "bytedance-seedance-2-0-image-to-video-fast",
  "version": "0.0.1",
  "input": {
    "prompt": "Smooth parallax zoom through the scene, crossfading into the second look",
    "image_url": "https://your-cdn.example.com/frame-start.jpg",
    "end_image_url": "https://your-cdn.example.com/frame-end.jpg",
    "duration": "6",
    "resolution": "720p"
  }
}
传入
end_image_url
锁定最终画面，模型会自动在起始帧和结束帧之间生成过渡动画：
json
{
  "model": "bytedance-seedance-2-0-image-to-video-fast",
  "version": "0.0.1",
  "input": {
    "prompt": "Smooth parallax zoom through the scene, crossfading into the second look",
    "image_url": "https://your-cdn.example.com/frame-start.jpg",
    "end_image_url": "https://your-cdn.example.com/frame-end.jpg",
    "duration": "6",
    "resolution": "720p"
  }
}

Polling

轮询结果

bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "X-API-Key: $EACHLABS_API_KEY"
StatusMeaning
processing
Still running — poll again
success
Done — read 
output
(video URL)
error
Failed — read 
message
/ 
details
bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "X-API-Key: $EACHLABS_API_KEY"
状态含义
processing
处理中 — 请再次轮询
success
处理完成 — 读取
output
字段获取视频URL
error
处理失败 — 读取
message
/ 
details
字段查看错误信息

Webhook (alternative to polling)

Webhook（轮询替代方案）

Pass 
"webhook_url": "https://your.host/path"
in the create body. EachLabs POSTs:
json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
status
is 
"succeeded"
or 
"failed"
. Return 2xx within 30 seconds.
在创建请求时传入
"webhook_url": "https://your.host/path"
。EachLabs会向该地址POST以下内容：
json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
status
的值为
"succeeded"
或
"failed"
。请在30秒内返回2xx状态码。

Parameters (both slugs share most of these)

参数说明（两种模型共享大部分参数）

ParameterTypeRequiredDefaultOptionsDescription
prompt
stringYes——Text prompt. For i2v, describes the motion/action; supports timeline prompting and dialogue lines for native audio.
image_url
stringYes (i2v only)—JPEG / PNG / WebP, max 30 MBStarting frame. Publicly reachable HTTPS URL.
end_image_url
stringNo (i2v only)—JPEG / PNG / WebP, max 30 MBFinal frame; model interpolates between 
image_url
and this.
resolution
stringNo
720p
480p
, 
720p
480p = faster/cheaper, 720p = balanced.
duration
stringNo
auto
auto
, 
4
…
15
Clip length in seconds. 
auto
lets the model pick from the prompt.
aspect_ratio
stringNo
auto
auto
, 
21:9
, 
16:9
, 
4:3
, 
1:1
, 
3:4
, 
9:16
For i2v, 
auto
infers from the input image.
generate_audio
booleanNo
true
—Synchronized SFX, ambience, and lip-synced speech. Cost is the same whether on or off.
seed
stringNo——Reproducibility hint — results may still drift slightly.
end_user_id
stringNo——Your end-user identifier.
参数类型是否必填默认值可选值描述
prompt
string是——文本提示词。对于图片转视频，用于描述动作/运镜；支持时间线提示和对话文本以生成原生音频。
image_url
string仅图片转视频必填—JPEG / PNG / WebP，最大30MB起始帧图片。需为可公开访问的HTTPS URL。
end_image_url
string否（仅图片转视频可用）—JPEG / PNG / WebP，最大30MB结束帧图片；模型会在
image_url
和该图片之间生成过渡动画。
resolution
string否
720p
480p
, 
720p
480p速度更快/成本更低，720p效果更均衡。
duration
string否
auto
auto
, 
4
…
15
视频片段时长（秒）。
auto
由模型根据提示词自动选择。
aspect_ratio
string否
auto
auto
, 
21:9
, 
16:9
, 
4:3
, 
1:1
, 
3:4
, 
9:16
对于图片转视频，
auto
会根据输入图片自动推断比例。
generate_audio
boolean否
true
—生成同步音效、环境音和唇形同步语音。无论开启与否，成本均相同。
seed
string否——用于结果复现的提示值——结果仍可能略有差异。
end_user_id
string否——你的终端用户标识符。

Pricing

定价

Dynamic, charged per second of output video:
ResolutionRate
480p$0.1129 / second
720p (default)$0.2419 / second
Audio generation does not change cost. A 6-second 720p clip ≈ $1.45; a 10-second 480p clip ≈ $1.13.
动态定价，按**输出视频时长（秒）**计费：
分辨率费率
480p$0.1129 / 秒
720p（默认）$0.2419 / 秒
音频生成不额外增加成本。一段6秒的720p视频约需$1.45；一段10秒的480p视频约需$1.13。

Prompt Tips

提示词技巧

  • Timeline prompting: sequence beats with time or cut words — "Wide shot: … Cut to close-up: … Finally: …". Seedance 2.0 respects temporal structure better than single-sentence prompts.
  • Dialogue with native audio: write the line in quotes and describe the speaker ("Weathered British male narrator, 50s, calm authoritative voice, says: …"). Lip-sync and ambience are generated in the same pass.
  • Camera language: use real film vocabulary ("slow push-in", "rack focus", "dolly left", "handheld", "crane up"). The model follows director-level cues.
  • Physics cues: mention weight, momentum, and material interactions ("dust scatters as boot lands", "fabric settles after the spin") to unlock the realistic-physics behavior.
  • 时间线提示：用时间或切换词划分镜头节奏——“全景：…… 切至特写：…… 最终：……”。Seedance 2.0相比单句提示词更能理解时间结构。
  • 带原生音频的对话：用引号写出台词并描述说话者（“50岁英国男性旁白，沉稳权威的声音，说道：……”）。唇形同步和环境音会同步生成。
  • 镜头语言：使用专业影视术语（“缓慢推近”、“焦点切换”、“向左跟拍”、“手持镜头”、“升降镜头”）。模型能遵循导演级的镜头指令。
  • 物理效果提示：提及重量、动量和材质交互（“靴子落地时尘土四散”、“旋转后布料缓缓落下”），以触发逼真的物理效果。

Rate Limits & Limits

速率限制与约束

LimitValue
Create requests100 / minute per key
Concurrent predictions10 per key
File inputsPublicly reachable HTTPS URLs only (JPEG/PNG/WebP, max 30 MB). No data-URIs, no localhost.
限制项数值
创建请求频率每个密钥每分钟100次
并发预测数每个密钥最多10个
文件输入限制仅支持可公开访问的HTTPS URL（JPEG/PNG/WebP，最大30MB）。不支持data-URIs或本地地址。

Errors

错误处理

Error body: 
{ "status": "error", "message": "...", "details": "..." }
CodeMeaning
400Invalid input
401Missing / invalid 
X-API-Key
404Unknown model or prediction id
429Rate limited — back off
5xxRetry with exponential backoff
错误响应体：
{ "status": "error", "message": "...", "details": "..." }
状态码含义
400输入参数无效
401
X-API-Key
缺失或无效
404模型或预测ID不存在
429请求超出速率限制 — 请稍后重试
5xx服务器错误 — 请使用指数退避策略重试

Security Constraints

安全约束

  • No arbitrary URL loading: 
    image_url
    / 
    end_image_url
    must point to your own HTTPS-reachable storage (S3, GCS, CDN). Do not forward user-pasted URLs without validation.
  • No third-party API tokens: never forward provider tokens through 
    input
    — authentication is exclusively via the EachLabs API key.
  • Validate before calling: resolve the live 
    request_schema
    via 
    GET /v1/model?slug=<slug>
    before constructing 
    input
    .
  • 禁止任意URL加载：
    image_url
    / 
    end_image_url
    必须指向你自己的HTTPS可访问存储（S3、GCS、CDN）。未验证前请勿直接使用用户粘贴的URL。
  • 禁止传递第三方API令牌：切勿通过
    input
    参数传递服务商令牌——身份验证仅通过EachLabs API密钥完成。
  • 调用前验证：在构造
    input
    参数前，先通过
    GET /v1/model?slug=<slug>
    获取最新的
    request_schema
    进行验证。

Parameter Reference

参数参考

See references/MODELS.md for the full per-slug table with defaults and options.
完整的模型参数表（含默认值和可选值）请查看references/MODELS.md。