wwwzhouhui avatar

Seedance Video Creator

This is a complete pipeline for turning text descriptions into storyboarded videos using Seedance 2.0 and the Jimeng API. It walks you through three stages: first generating professional storyboard prompts with time codes and camera movements, then calling a text-to-image API to create the first frame (since Seedance requires at least one reference image), and finally generating the actual video with those images and prompts. You'll need to run the jimeng-free-api-all Docker container and grab your sessionid from the Jimeng website. It handles 4-15 second videos, supports multiple aspect ratios, and automatically downloads everything. The conversational prompt engineering for shot composition and pacing is notably thorough, breaking down narrative, visual style, camera language, and sound design before assembly.

skills.sh installs
175
GitHub stars
294
last updated
Aug 21, 2026

Install

$ npx -y skills add wwwzhouhui/skills_collection --skill seedance-video-creator --agent claude-code

Installs into .claude/skills of the current project.

Files

Seedance 2.0 分镜视频创作工具

将创意想法转化为专业分镜提示词,通过即梦 API 先生成参考图,再基于图片+提示词生成视频、自动下载。


前置条件

使用本技能前,确保以下服务可用:

  1. jimeng-free-api-all 服务运行中(默认端口 8000)

    # Docker 部署
    docker run -it -d --init --name jimeng-free-api-all \
      -p 8000:8000 -e TZ=Asia/Shanghai \
      wwwzhouhui569/jimeng-free-api-all:latest
    
  2. 获取 SessionID:

  3. 环境变量(可选,也可在交互中指定):

    • JIMENG_API_URL:API 基础地址(默认 http://127.0.0.1:8000),注意只填基础地址,不要包含路径部分。如使用 duckcloud 服务则为 https://jimeng.duckcloud.fun
    • JIMENG_SESSION_ID:即梦 SessionID

核心能力

Seedance 2.0 特性

重要约束:Seedance 2.0 必须至少提供一张参考图片,不支持纯文本生成视频。当用户没有提供图片时,需要先通过文生图 API 生成首帧参考图。

多模态输入(最多12个文件):

  • 图片:≤9张(首帧/尾帧/角色/场景参考)
  • 视频:≤3个,总时长≤15s(运镜/动作/特效参考)
  • 音频:≤3个,总时长≤15s(配乐/音效/对白参考)
  • 文本:自然语言描述

视频参数:

  • 模型:seedance-2.0-fast(推荐,快速版)/ jimeng-video-seedance-2.0-fast(等价别名)/ jimeng-video-seedance-2.0(Pro版)/ seedance-2.0 / seedance-2.0-pro(Pro等价别名)
  • 比例:1:1 / 4:3 / 3:4 / 16:9 / 9:16 / 3:2 / 2:3 / 21:9
  • 分辨率:480p / 720p(默认)/ 1080p
  • 时长:4 - 15 秒

Sponsors

Details

Repository
github.com/wwwzhouhui/skills_collection
Category
Backend & APIs
First seen
Jun 3, 2026

More from wwwzhouhui/skills_collection

All 5
1samhvw8 avatarfrontend-developmentsamhvw8/dotfilesMulti-framework frontend development. Frameworks: React 18+ (Suspense, hooks, TanStack), Vue 3 (Composition API, Pinia, Nuxt), Svelte 5 (Runes, SvelteKit), Angu174skills.sh installs
2charleswiltgen avataraxiom-app-shortcuts-refcharleswiltgen/axiomUse when implementing App Shortcuts for instant Siri/Spotlight availability, configuring AppShortcutsProvider, adding suggested phrases, or debugging shortcuts 172skills.sh installs
3charleswiltgen avataraxiom-energy-refcharleswiltgen/axiomComplete energy optimization API reference - Power Profiler workflows, timer/network/location/background APIs, iOS 26 BGContinuedProcessingTask, MetricKit monit172skills.sh installs
4xmanrui avatarvoice-messagexmanrui/voice-messageSend voice messages across chat channels (Telegram, Discord, Feishu/Lark, Signal, WhatsApp, and others) using edge-tts for text-to-speech and ffmpeg for audio c172skills.sh installs
5aibtcdev avatarteneroaibtcdev/skillsTenero (formerly STXTools) market analytics — token info, market stats, top gainers/losers, wallet holdings and trades, trending DEX pools, whale trades, holder170skills.sh installs
6charleswiltgen avataraxiom-core-location-refcharleswiltgen/axiomUse for Core Location API reference - CLLocationUpdate, CLMonitor, CLServiceSession, authorization, background location, geofencing170skills.sh installs