seedance-video

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Seedance 视频生成

Seedance Video Generation

使用字节跳动 Seedance-1.5-pro 模型 (doubao-seedance-1-5-pro-251215) 根据文本或图片生成视频。

Generate videos from text or images using ByteDance's Seedance-1.5-pro model (doubao-seedance-1-5-pro-251215).

前置要求

Prerequisites

安装 SDK:

bash

pip install 'volcengine-python-sdk[ark]'

Install the SDK:

bash

pip install 'volcengine-python-sdk[ark]'

功能

Features

文生视频: 根据文本提示词生成视频
图生视频: 根据首帧图片生成视频
自定义参数: 支持设置时长、宽高比、水印等
任务管理: 创建任务、查询状态、自动下载

Text-to-video: Generate videos based on text prompts
Image-to-video: Generate videos based on the first frame image
Custom parameters: Support setting duration, aspect ratio, watermark, etc.
Task management: Create tasks, query status, and auto download results

使用方法

Usage

1. 快速生成视频 (文生视频)

1. Quick video generation (text-to-video)

bash

cd ~/.openclaw/workspace/skills/seedance-video
python3 scripts/generate_video.py "一只可爱的猫咪在草地上玩耍" --wait -o cat.mp4

bash

cd ~/.openclaw/workspace/skills/seedance-video
python3 scripts/generate_video.py "A cute cat playing on the grass" --wait -o cat.mp4

2. 自定义参数

2. Custom parameters

bash

python3 scripts/generate_video.py "日落时分的海边" \
  --duration 10 \
  --ratio 16:9 \
  --wait \
  -o sunset.mp4

bash

python3 scripts/generate_video.py "Seaside at sunset" \
  --duration 10 \
  --ratio 16:9 \
  --wait \
  -o sunset.mp4

3. 图生视频

3. Image-to-video

bash

python3 scripts/generate_video.py "猫咪动起来" \
  --image-url https://example.com/cat.jpg \
  --duration 5 \
  --wait

bash

python3 scripts/generate_video.py "Make the cat move" \
  --image-url https://example.com/cat.jpg \
  --duration 5 \
  --wait

4. 仅创建任务（不等待）

4. Create task only (no waiting)

bash

python3 scripts/generate_video.py "星空下的城市" -o starry.mp4

bash

python3 scripts/generate_video.py "City under the starry sky" -o starry.mp4

返回任务ID

Return task ID


然后稍后查询状态并下载：
```bash
python3 scripts/generate_video.py --status <task_id> --wait -o starry.mp4


Then query the status and download later:
```bash
python3 scripts/generate_video.py --status <task_id> --wait -o starry.mp4

参数说明

Parameter Description

参数	默认值	说明
`prompt`	必填	视频描述提示词
`-o, --output`	output.mp4	输出文件路径
`-m, --model`	doubao-seedance-1-5-pro-251215	模型 ID
`-d, --duration`	5	视频时长(秒)
`-r, --ratio`	16:9	宽高比 (16:9, 9:16, 1:1, 4:3 等)
`--watermark`	false	添加水印
`--return-last-frame`	false	返回最后一帧图片
`--image-url`	无	首帧图片 URL (图生视频)
`--wait`	false	等待视频生成完成并下载
`--status`	无	查询指定任务ID的状态

Parameter	Default Value	Description
`prompt`	Required	Video description prompt
`-o, --output`	output.mp4	Output file path
`-m, --model`	doubao-seedance-1-5-pro-251215	Model ID
`-d, --duration`	5	Video duration (seconds)
`-r, --ratio`	16:9	Aspect ratio (16:9, 9:16, 1:1, 4:3, etc.)
`--watermark`	false	Add watermark
`--return-last-frame`	false	Return the last frame image
`--image-url`	None	First frame image URL (for image-to-video)
`--wait`	false	Wait for video generation to complete and download automatically
`--status`	None	Query the status of the specified task ID

API 密钥配置

API Key Configuration

需要设置

ARK_API_KEY

或

SEEDANCE_API_KEY

环境变量。

You need to set the

ARK_API_KEY

SEEDANCE_API_KEY

environment variable.

配置方式（推荐）

Configuration Method (Recommended)

复制配置模板：

bash

cp .canghe-skills/.env.example .canghe-skills/.env

编辑
```
.canghe-skills/.env
```
文件，填写你的 API Key：

ARK_API_KEY=your-actual-api-key-here

Copy the configuration template:

bash

cp .canghe-skills/.env.example .canghe-skills/.env

Edit the
```
.canghe-skills/.env
```
file and fill in your API Key:

ARK_API_KEY=your-actual-api-key-here

或使用环境变量

Or use environment variables

bash

export ARK_API_KEY="your-api-key"

bash

export ARK_API_KEY="your-api-key"

或

Or

export SEEDANCE_API_KEY="your-api-key"

undefined

export SEEDANCE_API_KEY="your-api-key"

undefined

加载优先级

Loading Priority

系统环境变量 (
```
process.env
```
)
当前目录
```
.canghe-skills/.env
```
用户主目录
```
~/.canghe-skills/.env
```

System environment variables (
```
process.env
```
)
```
.canghe-skills/.env
```
in the current directory
```
~/.canghe-skills/.env
```
in the user home directory

提示词优化建议

Prompt Optimization Suggestions

根据 Seedance-1.5-pro 提示词指南：

具体描述: 描述场景、主体、动作、环境等细节
风格明确: 指定摄影风格（如"电影感"、"纪录片风格"）
光线描述: 说明光线条件（如"黄金时刻"、"柔和自然光"）
镜头语言: 描述镜头运动（如"缓慢推进"、"稳定器拍摄"）

Refer to Seedance-1.5-pro Prompt Guide:

Specific description: Describe details such as scene, subject, action, environment, etc.
Clear style: Specify the photography style (such as "cinematic", "documentary style")
Light description: Specify lighting conditions (such as "golden hour", "soft natural light")
Lens language: Describe camera movement (such as "slow push-in", "stabilizer shooting")

示例提示词

Example Prompts

一只金毛犬在秋天的公园里奔跑，金色落叶飘落，下午的阳光透过树叶，电影感镜头，稳定器拍摄，4K画质

一个机器人在未来城市的霓虹灯街道上行走，赛博朋克风格，雨夜，倒影，广角镜头，电影色调

A golden retriever running in an autumn park, golden fallen leaves falling, afternoon sunlight passing through the leaves, cinematic lens, stabilizer shooting, 4K quality

A robot walking on a neon street in a future city, cyberpunk style, rainy night, reflections, wide-angle lens, cinematic color tone

Python API 使用

Python API Usage

python

from volcenginesdkarkruntime import Ark
from scripts.generate_video import create_video_task, wait_for_video

python

from volcenginesdkarkruntime import Ark
from scripts.generate_video import create_video_task, wait_for_video

初始化客户端

Initialize client

client = Ark( base_url="https://ark.cn-beijing.volces.com/api/v3", api_key="your-api-key" )

创建视频任务

Create video task

result = create_video_task( client=client, model="doubao-seedance-1-5-pro-251215", prompt="一只鸟在天空中飞翔", duration=5 )

task_id = result["task_id"]

result = create_video_task( client=client, model="doubao-seedance-1-5-pro-251215", prompt="A bird flying in the sky", duration=5 )

task_id = result["task_id"]

等待并获取结果

Wait and get result

final_status = wait_for_video(client, task_id) video_url = final_status["video_url"]

undefined

final_status = wait_for_video(client, task_id) video_url = final_status["video_url"]

undefined

注意事项

Notes

异步生成: 视频生成是异步过程，通常需要 30-60 秒
任务保存时间: 任务数据仅保留 24 小时
限流: 注意账号的 RPM 和并发数限制
视频比例: 建议视频宽高比与首帧图片比例接近

Asynchronous generation: Video generation is an asynchronous process, usually taking 30-60 seconds
Task retention time: Task data is only retained for 24 hours
Rate limiting: Pay attention to the RPM and concurrency limits of your account
Video ratio: It is recommended that the video aspect ratio is close to the ratio of the first frame image

任务状态

Task Status

```
queued
```
: 排队中
```
running
```
: 生成中
```
succeeded
```
: 成功
```
failed
```
: 失败

```
queued
```
: In queue
```
running
```
: Generating
```
succeeded
```
: Succeeded
```
failed
```
: Failed