Seedance

Generate production-ready Chinese video prompts and image prompts for ByteDance Seedance 2.0 / 2.5 (即梦), and optionally execute them via the official dreamina CLI. Covers both versions — 2.0 (15s, 12 refs) and 2.5 (30s single-pass, up to 180s long-video mode, 50 refs, timestamp editing, green-screen reference, segment retake). Use when the user mentions "Seedance", "Seedance 2.5", "即梦", "即梦2.5", "小云雀", "豆包专业版", "30秒直出", "长视频模式", "片段重拍", "绿幕参考", "白模参考", "时间戳编辑", "视频提示词", "视频生成", "AI视频", "短剧", "广告视频", "视频延长", "角色图", "首帧图", "角色参考图", "生图", "运镜", "镜头", "景别", "机位", "推拉摇移", "四维编码", "Z轴", "Y轴", "X轴",

27 stars 1 forksImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add ye4wzp/seedance2.5-prompt-skill --skill seedance

Manual install

git clone --depth 1 https://github.com/ye4wzp/seedance2.5-prompt-skill.git /tmp/seedance2.5-prompt-skill
mkdir -p ~/.claude/skills
cp -r /tmp/seedance2.5-prompt-skill/. ~/.claude/skills/seedance

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Seedance 2.0 / 2.5 视频 & 图片提示词生成器

你是一个专业的 AI 视频与图片提示词工程师，为字节跳动即梦平台 **Seedance 2.0 / 2.5** 及配套图片生成平台（默认 **NanoBanana**，可切换为即梦图片生成）生成可直接使用的中文提示词。

**你的职责不是给用户的原话套上电影术语，而是替他把没做的决策做掉**——时长、路径、前 2 秒放什么、素材分工、审查风险。往里灌 `8K + Octane + 史诗级` 是注水，不是改写。概念本身不行时要**先说不**，不要把平庸想法翻译成措辞专业的平庸想法。

你的核心能力体系分为 **五大模块**：

| 模块 | 文件 | 核心用途 |
|:---|:---|:---|
| 📷 **相机四维编码** | [camera-codec.md](references/camera-codec.md) | 用 Z/Y/X/F 坐标精准控制任何镜头 |
| 🎨 **深度美学约束** | [aesthetic-constraints.md](references/aesthetic-constraints.md) | Octane 级渲染品质 + 冷暖色调系统 |
| 🎬 **长视频生产流水线** | [production-pipeline.md](references/production-pipeline.md) | 角色卡 → 分镜 → 逐镜头（含 25 格流水线） |
| ✂️ **AI 素材剪辑节奏** | [editing-rhythm.md](references/editing-rhythm.md) | 六套剪辑公式 + AI 素材专属对策 |
| 🖼️ **图片生成** | [image-generation.md](references/image-generation.md) | 角色卡片图、首帧图、关键帧图 |

> **先确认模型选对了**（用户没点名模型时）：需要**本地跑 / 开源权重 / 自控管线**，或要**精确音色克隆 + 口型对齐** → 改用 `minimax-h3` skill。
> 其余情况（尤其 >15 秒、中文口播、素材多、要上抖音）留在这里。用户点名即梦/Seedance/小云雀/豆包时跳过这步。

## 🔀 第 0 步：先判版本（2.0 / 2.5）

**2026-07-31 起即梦上线 Seedance 2.5，硬参数和方法论都有变化。动手前先确认用户在哪个版本。**

| 差异项 | 2.0 | 2.5 |
|:---|:---|:---|
| 单次时长 | 15s | **30s**（平台侧可延长至 90s，长视频模式最长 180s） |
| 参考素材 | 12 个（图9+视频3+音频3） | **50 个（图30+视频10+音频10）** |
| >15s 做法 | 分段生成 + 拼接 | **≤30s 单条直出；30–90s 平台延长；90–180s 长视频模式。三档都不用剪辑拼接** |
| 真人脸 | 一律拦截 | **认证后可用** |
| 新能力 | — | 时间戳编辑 / 绿幕·白模参考 / 片段重拍（单秒级） |

**用户没说版本 → 问一句。** 15s 和 30s 的分镜密度是两套写法，猜错整条重写。

Read the full skill on GitHub

Details

Skill name: seedance
Repository: ye4wzp/seedance2.5-prompt-skill
License: MIT
Repo updated: 7 August 2026

FAQ

What does the Seedance skill do?

How do I install the Seedance skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add ye4wzp/seedance2.5-prompt-skill --skill seedance. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Seedance popular?

It lives in ye4wzp/seedance2.5-prompt-skill, which has 27 GitHub stars and 1 forks.

Related skills

Unblind

Santazuki/unblind

Routes images to Mimo/OpenAI vision API for text-only models. Use this skill when the user sends an image, asks "what's in this picture", says "analyze this screenshot", requests "OCR" or "extract text", reviews UI designs, reads charts, or uses Chinese triggers like 识别图片/看图. Self-healing setup on first run. Does NOT handle video, audio, or PDFs.

Images, Video & Audio

Punk Ip Video Cover

adrianpunk/punk-ip-video-cover

从上传人物照片提取四个颜色并搭配，抠出真人，按主题与标题自由构图，制作小红书人物 IP 视频封面；从独立库选择字体、材质与装饰风格，允许动作表情修改，支持 3:4、16:9、4:3、9:16 和多个版本。也用于接入新风格和编写封面提示词。

Images, Video & Audio

Video Downloader

zyipeng/video-downloader

Downloads videos from YouTube and other platforms for offline use. Save videos locally for later viewing.

Images, Video & Audio

China Patent Figure Skill

PisenAILab/china-patent-figure-skill

Generate patent figures from a 3D CAD assembly (STEP) by writing one figure-plan.json that scripts render deterministically into assembly and exploded DXF sheets with leaders and reference numerals, and clean or convert existing patent line drawings (DWG, DXF, Matplotlib, PDF, raster) into continuous-line DXF plus an AutoCAD-audited DWG with reference numerals removed and functional labels preserved.

Images, Video & Audio

Video Sharingan

nikolasfaria/video-sharingan

Reverse-engineer the audiovisual production of a reference video (motion design, product launch, changelog, app promo, trailer) into measured numbers and a recreation brief. Use this when the user shares a video and says "make ours like this", "copy this style/camera/pacing", "what camera moves does this use", "how fast is the camera", "recreate this launch video", or before generating a video with Hyperframes, /brag, Remotion or After Effects from a reference. Measures cuts and shot durations, camera language (truck/pedestal/pan/push-in/pull-out/orbit, speed in px/s and %W/s, scale %/s, easin

Images, Video & Audio

Ascii Art

neethanwu/ascii-art

Converts text, images, or video to ASCII art with multiple styles and export formats. Use when the user asks to create ASCII art, convert images/videos to text art, or mentions ascii-art, braille art, or block art.

Images, Video & Audio

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.