zenstory-ai/drama-skills / skills/short-drama-video-prompts
short-drama-video-prompts
Verified把短剧分镜和首帧写成可直接复制的视频提示词,也可独立起草视频动作或成片配乐/主题曲提示词。用于文生/图生视频动作、人物表演、运镜、口型、环境动态、镜头时长与配乐提示词编写;不调生成接口、不写歌词、不改分镜起止状态。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.4 KB |
| agents/openai.yaml | config | 316 B |
| references/camera-audio-continuity.md | markdown | 5.2 KB |
| references/format-spec.md | markdown | 5.6 KB |
| references/minimax-h3.md | markdown | 10.9 KB |
| references/model-and-delivery-profiles.md | markdown | 7.4 KB |
| references/performance-action-timing.md | markdown | 4.6 KB |
| references/seedance-2.0.md | markdown | 4.2 KB |
| references/seedance-2.5.md | markdown | 5.7 KB |
| references/stage-contract.md | markdown | 7.2 KB |
| references/video-prompt-guide.md | markdown | 9.2 KB |
| references/wan-3.0.md | markdown | 5.0 KB |
references/seedance-2.0.md
View on GitHub# Seedance 2.0 提示词写法
在目标模型配置明确指定 `target_video_model: seedance-2.0` 时使用。推荐配置:
```json
{
"target_video_model": "seedance-2.0",
"video_prompt_dialect": "seedance-2.0",
"video_prompt_language": "zh-CN",
"native_duration_seconds": {"min": 4, "max": 15},
"supported_generation_modes": ["text", "first_frame", "first_last_frame", "reference", "extend"],
"audio_generation": "same_pass"
}
```
## 专属标记语法与多镜切法
- **镜头切分**:单镜按因果先后顺序连贯描写;多镜合生用 `镜头1:`、`镜头2:` 分段(**Seedance 2.0 只认镜头序号、不识别精确时间码**,需精确卡切点时优先逐镜单拍或出片后精剪)。
- **声音与字幕标记**:现场对白写 `{角色用中文说:“逐字台词”}`(保持单一口语语种,专有名词除外);动作音效写 `<声音>`,音乐写 `(音乐)`;需要显示画面外花字时才用 `【字幕】`,存在乱码叠字风险的场景按需补充“无字幕叠加”且正文不出现 `【】`,画内必读招牌或纸页文字写清所在物体表面与位置。
- **前景遮挡与画外视线**:写清机位架在哪一侧、谁在前景谁在后景、中间隔着什么陈设(避免笼统写“隔桌面对面”导致人物挤到同侧);看画外角色时点明“看向画外、对方不入画”。
## 三种互斥输入模式与素材编号
首帧(1 张图)、首尾帧(2 张图)与全模态参考(0–9 张图、≤3 段视频、≤3 段音频,音视频单段 2–15 秒且同类总长 ≤15 秒,音频不可单传)在**同一次生成中彼此互斥**:
- **锁构图 vs 多参考取舍**:要求把开场或收尾构图像素级锁死在某张关键帧上时,走**首帧或首尾帧模式**;需要同时挂角色设定图、关键道具图或参考音频时,统一走**全模态参考模式**——把开场关键帧作为 `@图片1` 传入时,须在 `输入参考图` 中将其 `用途` 由 `起始帧` 改标为 `构图`(避免映射为 `first_frame` 触发 2.0 模式互斥;未同挂对应条目 `主体` / `造型状态` 图时保留生效 `LOCK-...` 锁定词),并在正文写明“`@图片1` 作为开场画面”;挂载 `- 参考音频:` 时不可单传音频,须至少同传一张参考图。
- **标签复现与按焦选图**:`@图片N`、`@视频N`、`@音频N` 编号严格对应本镜同类参考项的 `顺序` 数字,正文中(含跨时段再次提及时)每次提到同一绑定素材均保持一致标签(如 `人物 @图片1`、`参考 @音频1 的音色`,台词引号内不塞入素材标签;《视频提示词.md》参考槽位仅登记图片与角色音色参考,传入 `@视频1` 参考运镜或续写均走外部平台手动提交 `relay_external`)。参考图超过 9 张上限时,按本镜景别与视觉焦点灵活取舍(近景特写优先保面部与手持道具图,全景调度优先保空间布局与全身图,见 [模型与交付配置](model-and-delivery-profiles.md))。
- **视频续写(外部手动提交 `relay_external`)**:需紧接上一段真实成片做连续动作延长时,在外部平台上传原片作为 `@视频1`,写明“向后延长 `@视频1`”并可搭配截取的真实尾帧 `@图片1` 稳住接缝姿态(不要笼统写成“参考 `@视频1`”)。
## 字数上限与支持时长
- **字数控制**:官方建议中文不超过 500 字、英文不超过 1000 词(过长易把顺嘴带到的背景摆设全塞进画面或触发意外硬切)。超限时优先删减已由参考图承载的静态背景铺垫,保留核心动作、锁定特征与逐字台词。
- **支持时长**:支持 **4–15 秒整数**或 `duration: -1` 自适应(上限仍为 15 秒);定长分镜直接传正整数秒,含对白镜头按 [台词时长估算](performance-action-timing.md#台词时长估算) 核对发声时间,出片后实测核查句尾是否完整。
依据(2026-09-07 核对;三种起点互斥、素材上限与正文字数建议 2026-10-20 核对):[视频生成 API](https://docs.volcengine.com/docs/82379/1520757)、[Seedance 2.5 指南中的 2.0/2.5 时间控制差异](https://docs.volcengine.com/docs/82379/2607689)。
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |