Doubao Seedance Video Generation

Use the script packaged with the skill to generate/edit videos via ByteDance Seedance video model on Volcengine Ark:

Doubao Seedance series video models (via Ark contents/generations/tasks interface)
Supports text-to-video, image-to-video (single / multiple image references)

Default Settings:

Default model:
```
doubao-seedance-1-5-pro-251215
```
(can be overridden with
```
--model
```
)
Default duration:
```
5
```
seconds
Default aspect ratio:
```
16:9
```

Text to Video

bash

uv run {baseDir}/scripts/generate_video.py \
  --prompt "一个在草地上奔跑的小狗视频，阳光明媚，电影感" \
  --filename "奔跑小狗.mp4"

Use YAML Configuration File

You can write all video generation parameters into a YAML configuration file and use it via the

--config

parameter:

Text-to-video configuration example (

text2video.yaml

yaml

prompt: 一个在草地上奔跑的小狗视频，阳光明媚，电影感
filename: 奔跑小狗.mp4
ratio: 16:9
duration: 5

Image-to-video configuration example (with URL reference image list,

image2video.yaml

yaml

prompt: 将图1的表情换为图2的表情，做一个眨眼微笑的短视频
filename: 表情女孩.mp4
images:
  - https://ark-project.tos-cn-beijing.volces.com/doc_image/seedream4_imagesToimage_1.png
  - https://ark-project.tos-cn-beijing.volces.com/doc_image/seedream4_5_imagesToimage_2.png
ratio: 9:16
duration: 5

Local reference image configuration example (

local_images.yaml

yaml

prompt: 多图融合成一个动画短片
filename: 多图融合动画.mp4
images:
  - /path/to/参考图1.jpg
  - /path/to/参考图2.png
ratio: 16:9
duration: 8

Usage:

bash

uv run {baseDir}/scripts/generate_video.py --config image2video.yaml

Mix configuration file and command line parameters (command line parameters have higher priority):

bash

uv run {baseDir}/scripts/generate_video.py --config prompt.yaml --filename "自定义文件名.mp4"

All parameters supported by YAML configuration file:

```
prompt
```
: Video content description
```
filename
```
: Output file name
```
images
```
: Reference image list (can be URL or local file path)
```
ratio
```
: Aspect ratio (e.g. "16:9", "9:16")
```
duration
```
: Video duration (seconds)
```
model
```
: Full model name (advanced option)
```
api_key
```
: API key

Image to Video / Reference Images (URL or local files are supported, multiple images, use lite i2v model)

bash

uv run {baseDir}/scripts/generate_video.py \
  --prompt "参考图片中的女孩，做一个挥手微笑的短视频" \
  --filename "挥手女孩.mp4" \
  -i "https://example.com/ref_image_1.png" \
  -i "/path/to/local_ref_2.jpg" \
  --ratio "9:16" \
  --duration 8

Use only reference images (no explicit text prompt)

bash

uv run {baseDir}/scripts/generate_video.py \
  --filename "仅参考图生成视频.mp4" \
  -i "/path/to/ref1.jpg" \
  -i "/path/to/ref2.png"

Tip: At least one of "prompt" or "reference image" is required, otherwise the script will report an error.

Notes

API Key

You need to set the
```
ARK_API_KEY
```
environment variable

Parameter Description

prompt: Video content text (supports Chinese / English)
image / -i:
- URL: Pass directly to Ark (e.g. publicly accessible image link)
- Local file: Automatically read and converted to
```
data:image/...;base64,...
```
  format before sending
- Can be passed multiple times to form multi-image reference (multi-image currently only works under lite i2v models such as
```
doubao-seedance-1-0-lite-i2v-250428
```
  )
ratio: Aspect ratio, commonly used:
- ```
"16:9"
```
  (default)
- ```
"9:16"
```
- ```
"1:1"
```
- ```
"21:9"
```
duration: Video duration (seconds), determined by the actual supported range of the model / Endpoint
model (optional, advanced): Directly specify Ark Endpoint / model ID to override the default binding

Additional parameters for polling script

get_video_task_status.py

interval: Polling interval (seconds), default
```
10
```
, can be adjusted according to task duration and frequency requirements
timeout: Maximum waiting time (seconds), default
```
600
```
, the script will report an error and exit after exceeding

Result and File Output

Ark video generation is usually an asynchronous task:
- The script will call
```
POST /contents/generations/tasks
```
- On success, the returned
```
id
```
  /
```
task_id
```
  will be parsed first as the task ID
- If
```
video_url
```
  is directly carried in the response body, the script will try to pull and save the video locally
Save path rules:
- If
```
--filename
```
  does not specify a directory, it will be saved to the
```
outputs/
```
  directory under this repository by default
- If the file name has no suffix,
```
.mp4
```
  will be added by default

If the call is successful but the backend only returns the task ID and

video_url

has not been generated, the script will output the task ID, which can be used together with the polling script:

bash

# 1) Create a task first (may only return TASK_ID)
uv run {baseDir}/scripts/generate_video.py \
  --prompt "一个示例视频" \
  --filename "示例视频.mp4"

# 2) After getting the TASK_ID output from the previous step, poll until generation is complete and download the video
uv run {baseDir}/scripts/get_video_task_status.py \
  cgt-20260226184301-4h8v6 \
  --filename "示例视频.mp4" \
  --interval 5

The polling script will:

Periodically call

GET /contents/generations/tasks/{task_id}

to check task status

When the status is
```
succeeded
```
/
```
completed
```
and
```
video_url
```
is obtained, automatically download the video to local

Recommended file names (for caller reference)

Do not include specific implementation details in the file name (such as "seedance", "ark", etc.)
It is recommended that the file name language is consistent with the Prompt language, for example, use a short Chinese file name for Chinese Prompt (e.g.
```
挥手女孩.mp4
```
)
The file name should be semantic and as short as possible, avoid overly long sentences

Keyword tips (for easy discovery / search hit)

"doubao", "豆包", "Seedance"
"ByteDance video model", "字节跳动视频生成"
"文生视频", "图生视频", "视频生成", "短视频生成"

generate-video-by-seedance

NPX Install

Tags

SKILL.md Content (Chinese)

Doubao Seedance Video Generation

Text to Video

Use YAML Configuration File

Text-to-video configuration example (
`text2video.yaml`
):

Image-to-video configuration example (with URL reference image list,
`image2video.yaml`
):

Local reference image configuration example (
`local_images.yaml`
):

Usage:

Mix configuration file and command line parameters (command line parameters have higher priority):

All parameters supported by YAML configuration file:

Image to Video / Reference Images (URL or local files are supported, multiple images, use lite i2v model)

Use only reference images (no explicit text prompt)

Notes

API Key

Parameter Description

Result and File Output

Recommended file names (for caller reference)

Keyword tips (for easy discovery / search hit)

generate-video-by-seedance

NPX Install

Tags

SKILL.md Content (Chinese)

Doubao Seedance Video Generation

Text to Video

Use YAML Configuration File

Text-to-video configuration example (text2video.yaml):

Image-to-video configuration example (with URL reference image list, image2video.yaml):

Local reference image configuration example (local_images.yaml):

Usage:

Mix configuration file and command line parameters (command line parameters have higher priority):

All parameters supported by YAML configuration file:

Image to Video / Reference Images (URL or local files are supported, multiple images, use lite i2v model)

Use only reference images (no explicit text prompt)

Notes

API Key

Parameter Description

Result and File Output

Recommended file names (for caller reference)

Keyword tips (for easy discovery / search hit)

Text-to-video configuration example (
`text2video.yaml`
):

Image-to-video configuration example (with URL reference image list,
`image2video.yaml`
):

Local reference image configuration example (
`local_images.yaml`
):