seedance-video-gen

Seedance2.0

Overview

Seedance2.0 is an AI video generation tool based on the Volcano Ark Seedance 2.0 model. Through the redfox.hk platform, the complex ARK API authentication process is encapsulated,generate a video with a single command。

Skill Features

Supports command-line parameterized control of resolution, aspect ratio, and duration

Dual mode: text-to-video + virtual avatar reference

Why use this Skill?

For developers: no need to apply for a whitelist from Volcano Ark, configure AK/SK, or integrate ARK authentication; one command gets it done
For creators: no need to buy a membership or bind a card for a subscription; pay per use, leave when done
For everyone: extremely low barrier, ready to use upon registration, no need to build the API pipeline yourself

Target Users

Social media creators, product managers, content operations staff, AI enthusiasts, and any users who need to quickly turn copy into video.

Features

Core Features

Text-to-video: enter a Chinese or English description, and Seedance 2.0 automatically generates an MP4 video with synchronized audio
Parameter control: supports resolution (480p/720p/1080p), aspect ratio (16:9/9:16 and 7 others), and video duration (4-15 seconds)
Virtual avatar: supports referencing preset virtual avatars via the asset:// format, with no need to upload real face material
Task management: supports obtaining a taskId after submitting a task, and you can query task progress and results at any time
Automatic polling: the script automatically polls task status (queued/generating/completed), with no need to wait manually

Technical Highlights

Underlying model:doubao-seedance-2-0-260128
Synchronized audio generation: video visuals and sound are output in sync
Last frame extraction: supports returning the last frame of the video for continuous video generation
Random seed: supports setting a seed value so results are reproducible
HTTPS secure transmission: full-chain SSL verification

Parameter Quick Reference

Parameter	Description	Default Value
`prompt`	Video prompt (required, Chinese or English)	—
`--resolution`	Resolution:`480p` / `720p` / `1080p`	`720p`
`--ratio`	Aspect ratio:`16:9` / `4:3` / `1:1` / `3:4` / `9:16` / `21:9` / `adaptive`	`16:9`
`--duration`	Video duration (seconds): 4-15 or -1 (smart)	`5`
`--seed`	Random seed: -1 to 2147483647	`-1`
`--no-audio`	Do not generate sound	Generated by default
`--watermark`	Add watermark	Not added by default
`--return-last-frame`	Return the last frame image URL	Not returned by default
`--image-url`	Reference image URL (`asset://` format)	—
`-o, --output-dir`	Output directory	`~/Downloads/QoderVideos`
`--prefix`	Filename prefix	`video`
`--no-download`	Submit only without waiting	—
`--task-id`	Query an existing task	—

Use Cases

Scenario 1: Social media content creation

Role: short video blogger / Xiaohongshu operator

Requirement: Quickly generate vertical-screen (9:16) video materials for publishing on Douyin/Xiaohongshu/WeChat Channels

How to Use：

python3 "$SKILL_PATH/scripts/videogen.py" "美妆产品展示，柔和的灯光，产品缓缓旋转" --ratio 9:16

Expected Benefits: Reduce material production costs, from several hours to a few minutes

Scenario 2: Product Feature Demonstration

Role: Product Manager / Entrepreneur

Requirement: Quickly generate product concept videos for proposals, pitch decks, or presentations

How to Use：

python3 "$SKILL_PATH/scripts/videogen.py" "一款智能手表在桌面上展示，表盘切换不同功能界面" --resolution 1080p --duration 8

Expected Benefits: No professional video production skills required; copy becomes video

Scenario 3: Brand Content Operations

Role: Content Operations / Marketing Staff

Requirement: Batch-generate brand background videos, paired with copy to create brand promotional short films

How to Use：

python3 "$SKILL_PATH/scripts/videogen.py" "品牌主题色背景，文字渐变浮现，专业大气" --ratio 16:9 --no-audio

Expected Benefits: Improve content output efficiency and unify brand visual style

Scenario 4: Rapid Validation of Creative Inspiration

Role: Designer / Creative Staff

Requirement: Quickly turn mental imagery into visualized videos using natural language to validate creative direction

How to Use：

python3 "$SKILL_PATH/scripts/videogen.py" "赛博朋克风格的城市夜景，霓虹灯闪烁，雨滴落在镜头上的效果" --duration 6

Expected Benefits: Lower the creative threshold; from idea to video in just one line of command

Scenario 5: Education and Training Visualization

Role: Teacher / Trainer

Requirement: Transform abstract knowledge points into visualized short films to improve teaching effectiveness

How to Use：

python3 "$SKILL_PATH/scripts/videogen.py" "太阳系行星围绕太阳旋转的动画，标注每颗行星的名称" --duration 10

Expected Benefits: No animation production skills required; zero threshold for knowledge visualization

First-Time Use

Available after configuring the API Key:

# 设置环境变量
export REDFOX_API_KEY=ak_你的密钥

# 运行
python3 "$SKILL_PATH/scripts/videogen.py" "一只橘猫在窗台上打哈欠，阳光温暖地照在它的毛上"

Go to redfox.hk to register and obtain an API Key.

Subsequent Use

You can go to redfox.hk to register an account and obtain your own API Key. Choose one of three configuration methods:

Configuration Method	Description	Command
Environment Variable(Recommended)	Set once, effective globally	`export REDFOX_API_KEY=ak_你的密钥`
Command-Line Parameter	Temporary use, effective for a single run	`python3 "$SKILL_PATH/scripts/videogen.py" "prompt" --api-key ak_你的密钥`
Configuration File	Persistent storage, retained across sessions	`mkdir -p ~/.qoder/apis && echo '{"api_key":"ak_你的密钥"}' > ~/.qoder/apis/redfox.json`

One-Click Installation

Dependency Installation

pip3 install requests

Environment Variables

Variable Name	Required	Description
`REDFOX_API_KEY`	—	API access key for the redfox.hk platform

Usage Guide

Basic Usage

1. Enter a prompt to generate a video

python3 "$SKILL_PATH/scripts/videogen.py" "一只橘猫在窗台上打哈欠，阳光温暖地照在它的毛上"

The script will automatically submit the task and poll for completion (about 3-15 minutes), then download it to ~/Downloads/QoderVideos/。

2. View Results

After successful generation, the video information and file path will be displayed:

[✓] Video ready: 5s, 720p, 16:9
[✓] Token usage: 108900
[→] Downloading video: video.mp4
[✓] Done!
  /Users/you/Downloads/QoderVideos/video.mp4 (2.5 MB)

Advanced Usage

Vertical Short Video (Compatible with Douyin/Xiaohongshu)

python3 "$SKILL_PATH/scripts/videogen.py" "时尚都市夜景，霓虹灯闪烁" --ratio 9:16

HD Long Video

python3 "$SKILL_PATH/scripts/videogen.py" "海浪拍打岩石的慢动作" --resolution 1080p --duration 10

Use Preset Avatars

python3 "$SKILL_PATH/scripts/videogen.py" "一位年轻女性在图书馆安静阅读" --image-url "asset://female_student_01"

For more preset avatar IDs, please refer to the Volcano Ark "Materials & Avatar Library" documentation.

Task Management

# 仅提交任务，返回 taskId 后立即退出
python3 "$SKILL_PATH/scripts/videogen.py" "复杂场景" --no-download

# 稍后用 taskId 查询结果
python3 "$SKILL_PATH/scripts/videogen.py" "ignored" --task-id vg_abc123def456

Multi-Segment Continuous Video Generation

# 1. 生成第一段，获取尾帧
python3 "$SKILL_PATH/scripts/videogen.py" "开场画面" --return-last-frame

# 2. 将返回的 lastFrameUrl 作为下一段的首帧
python3 "$SKILL_PATH/scripts/videogen.py" "转场到第二个场景" --image-url "上一步的lastFrameUrl"

Command Quick Reference

Command	Function
`python3 videogen.py "提示词"`	Basic text-to-video
`--ratio 9:16`	Vertical aspect ratio
`--resolution 1080p`	HD resolution
`--duration 10`	Specify duration
`--no-audio`	Silent video
`--watermark`	Add watermark
`--seed 42`	Fixed seed for reproducibility
`--image-url "asset://..."`	Reference virtual persona
`--no-download`	Submit task only
`--task-id <id>`	Query existing task
`--api-key <key>`	Specify API Key
`-o ~/Desktop`	Specify output directory

Project architecture

Directory structure

seedance-video-gen/
├── SKILL.md              # Skill 定义与文档
└── scripts/              # 工具脚本
    └── videogen.py       # 视频生成主程序

Tech stack

Component	Technology
Runtime environment	Python 3.6+
HTTP library	requests
API platform	redfox.hk
Underlying model	Volcano Ark Seedance 2.0 (doubao-seedance-2-0-260128)
Output format	MP4

Core modules

Module	Responsibility
`get_api_key()`	Three-level priority for obtaining API Key: CLI > environment variable > configuration file
`submit_video_task()`	Build the content array and submit the video generation task
`poll_video_result()`	Poll task status (queued/running/succeeded/failed/expired), up to 20 minutes
`download_video()`	Stream-download the MP4 video with a progress bar display
`main()`	CLI entry: argument parsing, API Key validation, dual-branch (submit/query) flow

Data flow

用户输入提示词 → submit_video_task() → redfox.hk API → 火山方舟 Seedance 2.0
                                                                      ↓
用户获得 MP4 ← download_video() ← poll_video_result() ← 任务完成回调

FAQ

Installation-related questions

Q1: Do I need an API Key?

A: Yes. Go to redfox.hk to register and obtain your own API Key, and configure it via the environment variable REDFOX_API_KEY or the --api-key parameter.

Q2: Where should the configuration file be placed?

A: Place it in ~/.qoder/apis/redfox.json, with the following content format:{"api_key": "ak_你的密钥"}。

Q3: How do I verify whether the API Key is configured successfully?

A: Run python3 videogen.py "测试" --no-download. If it returns a taskId, the configuration is successful.

Usage-related questions

Q4: How long does it take to generate a video?

A: Usually 3-15 minutes; complex scenes may take longer. The script will automatically poll and wait, up to 20 minutes.

Q5: Does it support uploading my own reference images?

A: Seedance 2.0 does not support directly uploading reference images/videos containing real human faces. If you need to specify a person's appearance, you can describe it in the prompt (e.g., "an Asian woman wearing glasses"), or use the asset:// URL of a preset virtual persona library. For more information, please refer to the Volcano Ark "Materials & Virtual Persona Library" documentation.

Q6: Which prompt languages are supported?

A: Both Chinese and English are supported; the API handles this automatically internally.

Q7: Where are the output files saved?

A: By default, they are saved to ~/Downloads/QoderVideos/video.mp4, and the directory can be specified via the -o parameter.

Troubleshooting

Q8: What should I do if the task times out?

A: The script waits up to 20 minutes. After a timeout, it will print the taskId, and you can later query and download the result again via the --task-id parameter.

Q9: It says "API request failed"?

A: Check whether the network connection is normal and confirm that the redfox.hk service is accessible. If it continues to fail, the API Key may have expired or there may be insufficient balance.

Q10: Video download failed?

A: Confirm that the output directory has write permission and sufficient disk space. If the OSS link has expired, you can use --task-id to query again and obtain a new download link.

Get Help

If you have other questions, you can go to redfox.hk to view the platform documentation or contact customer service.

About this skill

Overview

Why use this Skill?

Target Users

Features

Core Features

Technical Highlights

Parameter Quick Reference

Use Cases

Scenario 1: Social media content creation

Scenario 2: Product Feature Demonstration

Scenario 3: Brand Content Operations

Scenario 4: Rapid Validation of Creative Inspiration

Scenario 5: Education and Training Visualization

First-Time Use

Subsequent Use

One-Click Installation

Dependency Installation

Environment Variables

Usage Guide

Basic Usage

1. Enter a prompt to generate a video

2. View Results

Advanced Usage

Vertical Short Video (Compatible with Douyin/Xiaohongshu)

HD Long Video

Use Preset Avatars

Task Management

Multi-Segment Continuous Video Generation

Command Quick Reference

Project architecture

Directory structure

Tech stack

Core modules

Data flow

FAQ

Installation-related questions

Usage-related questions

Troubleshooting

Get Help