openakita/skills@seedance-video
Generate AI videos using ByteDance Seedance models via Volcengine Ark API.
Skill by openakita
Chalk Labs
Need help deploying openakita/skills@seedance-video?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/openakita-openakita-skills-seedance-video
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend, ml, writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 2
ark.cn-beijing.volces.com· found in codecodeload.github.com· found in install command
Files it touches
~/.claude/skills/openakita-skills-seedance-video
What's inside
- Skill name
openakita/skills@seedance-video- Description
- Generate AI videos using ByteDance Seedance models via Volcengine Ark API. Supports text-to-video, image-to-video (first frame, first+last frame), multimodal reference (images+videos+audio), video editing, video extension, web search enhancement, audio generation, draft mode, offline inference, and continuous video chaining. Use when user wants to generate, create, edit, or extend AI videos from text prompts, images, videos, or audio.
- License
- MIT
- Metadata
- author: openakita · version: 2.1.0
- Instructions
- 190 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
- Instructions call the network
Agent Skills spec issues
- name: only lowercase letters, digits and single hyphens allowed
- name: "openakita/skills@seedance-video" does not match folder "seedance-video"
Files (6)
- SKILL.md
- openai.yaml · agents/
- doc.md
- api-params.md · references/
- seedance.py · scripts/
- 视频生成教程.md
SKILL.md (first lines)
# Seedance 视频生成
通过火山方舟 Ark API 使用字节跳动 Seedance 模型生成 AI 视频。
## 前置条件
需设置 ARK_API_KEY 环境变量:
export ARK_API_KEY="your-api-key-here"
Base URL: https://ark.cn-beijing.volces.com/api/v3
## 支持模型
| 模型 | 模型 ID | 能力 |
|------|---------|------|
| Seedance 2.0 | doubao-seedance-2-0-260128 | 全能力:文/图/多模态/编辑/延长/联网/有声 |
| Seedance 2.0 Fast | doubao-seedance-2-0-fast-260128 | 同 2.0,更快更便宜 |
| Seedance 1.5 Pro | doubao-seedance-1-5-pro-251215 | 文生视频、图生视频、音频、草稿模式、离线推理 |
| Seedance 1.0 Pro | doubao-seedance-1-0-pro-250528 | 文生视频、图生视频、离线推理 |
| Seedance 1.0 Pro Fast | doubao-seedance-1-0-pro-fast-251015 | 同 1.0 Pro,更快 |
| Seedance 1.0 Lite T2V | doubao-seedance-1-0-lite-t2v-250428 | 仅文生视频 |
| Seedance 1.0 Lite I2V | doubao-seedance-1-0-lite-i2v-250428 | 图生视频、参考图 |
默认模型: doubao-seedance-2-0-260128
## Seedance 2.0 能力总览
- **文生视频**: 纯文本 prompt 生成视频
- **图生视频**: 首帧(first_frame) / 首尾帧(first_frame+last_frame)
- **多模态参考**: 组合图片(0-9张)、视频(0-3个)、音频(0-3个)
- **视频编辑**: 替换主体、增删改对象、局部重绘/修复
- **视频延长**: 向前/向后延长、多段串联
- **联网搜索**: 纯文本模式 web_search,提升时效性
- **有声视频**: generate_audio=true 生成同步音频
- **返回尾帧**: return_last_frame=true 获取视频尾帧(用于连续生成)
## Content 结构
Ark API 使用 content 数组传递多模态输入:
| type | 子字段 | role | 说明 |
|------|--------|------|------|
| text | text | — | 文本提示词 |
| image_url | image_url.url | first_frame | 首帧图片 |
| image_url | image_url.url | last_frame | 尾帧图片 |
| image_url | image_url.url | reference_image | 参考图片(2.0 多模态) |
| video_url | video_url.url | reference_video | 参考视频(2.0 编辑/延长/多模态) |
| audio_url | audio_url.url | reference_audio | 参考音频(2.0 多模态) |
**素材引用规则**: 提示词中使用"素材类型+序号"引用,如「图片1」「视频2」「音频1」。序号为同类素材在 content 数组中的排序(从1开始)。不支持用 Asset ID 指代素材。
## 提示词技巧
### 基本公式
**提示词 = 主体 + 运动,背景 + 运动,镜头 + 运动**
### 通用建议
- 用简洁准确的自然语言描述想要的效果
- 将抽象描述换成具象描述,重要内容前置
- 文生视频随机性较大,可用于激发灵感
- 图生视频请尽量上传高清高质量图片
- 如有明确预期,建议先生图再图生视频
### 2.0 多模态参考公式
- **图片参考**: 参考/提取/结合「图片n」中的「主体描述」,生成「画面描述」,保持特征一致
- **视频参考**: 参考「视频n」的「动作/运镜/特效描述」,保持一致
- **音频参考**: 音色 → 「角色」说:"「台词」",音色参考「音频n」;内容 → 时机+「音频n」
### 2.0 视频编辑公式
- **增加元素**: 描述「元素特征」+「出现时机」+「出现位置」
- **删除元素**: 点明删除目标,强调保持不变的元素
- **修改元素**: 清晰描述更换内容
### 2.0 视频延长公式
- **单段延长**: 向前/向后延长「视频n」+「延长内容描述」
- **多段串联**: 「视频1」+「过渡描述」+接「视频2」+「过渡描述」+接「视频3」
## 参数参考
| 参数 | 类型 | 默认值 | 说明 |
|------|------|--------|------|
| ratio | string | 16:9 | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive |
| duration | int | 5 | 视频时长:2.0=4-15s, 1.5=4-12s, 1.0=2-12s |
| resolution | string | 720p | 480p, 720p (2.0); 480p, 720p, 1080p (1.x) |
| generate_audio | bool | true | 生成同步音频 |
| watermark | bool | false | 添加水印 |
| seed | int | — | 随机种子(复现结果) |
| camera_fixed | bool | false | 固定摄像头(1.x) |
| draft | bool | false | 草稿模式,低成本预览(仅 1.5 Pro) |
| return_last_frame | bool | false | 返回视频尾帧(用于连续生成) |
| tools | array | — | [{"type":"web_search"}] 联网搜索(仅 2.0 纯文本) |
| service_tier | string | default | default=在线推理, flex=离线推理半价(仅 1.5 Pro / 1.0 系列) |
| execution_expires_after | int | 172800 | 离线任务超时秒数(flex 模式生效) |
| callback_url | string | — | Webhook 回调 URL,任务状态变化时通知 |
## 进阶用法
### 离线推理(半价)
设置 service_tier="flex",价格仅为在线推理的 50%。仅 1.5 Pro 和 1.0 系列模型支持,2.0 不支持。适合时延不敏感的批量生成场景。
### 样片模式(两步走)
1. draft=true 生成低成本预览视频,验证构图/镜头/动作
2. 确认后用 draft 视频 URL 作为 reference_video 生成正式视频
### 连续视频生成
设置 return_last_frame=true,用前一个视频的尾帧作为下一个视频的首帧,循环生成多段连续视频。可用 FFmpeg 拼接成长视频。
## 使用限制
- **图片**: jpeg/png/webp/bmp/tiff/gif/heic/heif, 300-6000px, <30MB, 宽高比 0.4-2.5
- **视频**: mp4/mov, 2-15s/个, 最多3个, 总时长≤15s, <50MB/个
- **音频**: wav/mp3, 2-15s/个, 最多3个, 总时长≤15s, <15MB/个
- **不支持组合**: "文本+音频"、"纯音频"输入
- **视频 URL 24h 过期**, 需立即下载
- **2.0 不支持上传含真人人脸的参考图/视频**, 可用虚拟人像(asset://ASSET_ID)
## 预置脚本
本 skill 提供 Python CLI(纯 stdlib,零依赖):`scripts/seedance.py`From openakita/openakita, MIT.
More from openakita/openakita
- 0.781score
openakita/skills@baidu-picture-book
baidu
AI Picture Book generation skill.
SkillBFreshness: B★ 2KClaude Code +9 - 0.781score
openakita/skills@amap-maps
AMap-Web
Amap (Gaode) Maps comprehensive service for POI search, route planning, travel planning, nearby search, heatmap visualization, and geocoding.
SkillBFreshness: B★ 2KClaude Code +9 - 0.781score
openakita/skills@baidu-paddleocr-text
baidu
PaddleOCR text recognition skill using PP-OCRv5 lightweight model.
SkillBFreshness: B★ 2KClaude Code +9 - 0.781score
openakita/skills@baidu-baike
baidu
Baidu Baike encyclopedia search skill.
SkillBFreshness: B★ 2KClaude Code +9 - 0.781score
openakita/skills@baidu-deep-research
baidu
Qianfan Deep Research Agent for complex research tasks.
SkillBFreshness: B★ 2KClaude Code +9 - 0.781score
openakita/skills@baidu-ecommerce
baidu
Baidu E-commerce skill for cross-platform price comparison, review analysis, and purchase knowledge.
SkillBFreshness: B★ 2KClaude Code +9 - 0.781score
openakita/skills@baidu-famou
baidu
Baidu FaMou algorithm skills for efficient algorithm self-evolution.
SkillBFreshness: B★ 2KClaude Code +9 - 0.781score
openakita/skills@baidu-maps
baidu
Baidu Maps skill for location search, nearby place search, geocoding, route planning, and weather queries.
SkillBFreshness: B★ 2KClaude Code +9 - 0.781score
openakita/skills@baidu-marketing
baidu
Baidu Intelligent Cloud marketing skill for generating marketing notes, videos, and optimized copy.
SkillBFreshness: B★ 2KClaude Code +9 - 0.781score
openakita/skills@baidu-netdisk
baidu-netdisk
Baidu Netdisk (Baidu Cloud) file management skill.
SkillBFreshness: B★ 2KClaude Code +9 - 0.781score
openakita/skills@baidu-paddleocr-doc
baidu
PaddleOCR document parsing skill based on PaddleOCR-VL-1.5.
SkillBFreshness: B★ 2KClaude Code +9 - 0.781score
openakita/skills@baidu-ppt-gen
baidu
AI PPT Generator skill.
SkillBFreshness: B★ 2KClaude Code +9
Signals
- Stars
- 2,005
- Forks
- 282
- Open issues
- 39
- Last commit (this folder)
- Jun 13, 2026 (4 months ago)
- Last release
- Sep 15, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 2.1.0
- License
- MIT
- Repository
- github.com/openakita/openakita
- Website
- openakita.ai
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from openakita
- 0.682score
smtp-email-sender
openakita
Send emails via SMTP (Gmail, Outlook, etc.).
SkillBFreshness: B★ 2KClaude Code +9 - 0.677score
get-chat-history
openakita
Get current chat history including user messages, your replies, and system task notifications.
SkillBFreshness: B★ 2KClaude Code +9 - 0.677score
cancel-scheduled-task
openakita
PERMANENTLY DELETE scheduled task.
SkillBFreshness: B★ 2KClaude Code +9 - 0.677score
deliver-artifacts
openakita
Deliver artifacts (files/images/voice) to current IM chat via gateway, returning a receipt.
SkillBFreshness: B★ 2KClaude Code +9 - 0.677score
export-agent
openakita
Export a local Agent profile as a portable .akita-agent package file.
SkillBFreshness: B★ 2KClaude Code +9 - 0.677score
get-image-file
openakita
Get local file path of image sent by user.
SkillBFreshness: B★ 2KClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get openakita/skills@seedance-video running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
openakita/skills@seedance-video. Agent Mart. https://agentmart.dev/skills/openakita-openakita-skills-seedance-video (last updated 2026-10-24)