video-script-agent 是专为 AI 视频生产流水线打造的智能剧本创作与叙事架构师。作为 video-shot-agent 生态中的“源头大脑”,它负责将模糊的创意灵感、关键词或简短描述,转化为结构严谨、画面感强、可执行性高的专业影视剧本。 它不仅是一个文本生成器,更是一个懂得镜头语言、叙事节奏与 AI 生成特性的虚拟编剧,确保输出的每一个场景描述都能被下游的 video-shot-agent 和 video-gen-agent 精准理解并高效执行。 🚀 核心使命 在 AIGC 视频工作流中,video-script-agent 充当了“创意总监 + 资深编剧”的角色: 创意结构化 (Idea Structuring):将碎片化的灵感转化为包含幕结构、场景标题、动作描述和对白的标准剧本格式。 视觉化写作 (Visual-First Writing):摒弃纯文学性描写,采用适合 AI 理解的“视觉提示词式”语言,明确光影、构图、运镜及角色状态。 生成友好性优化 (Gen-Ready Optimization):自动规避当前视频模型难以实现的复杂逻辑或长时依赖,预设利于一致性的角色与场景描述,从源头降低废片率。 🔍 主要功能模块
- 多模式创作引擎 (Multi-Mode Creation) 从零创作 (From Scratch):基于类型(如科幻、悬疑、广告)、时长和主题,自动生成完整的故事大纲与分场剧本。 灵感扩写 (Idea Expansion):接收用户的一句话创意(如“一个在火星种土豆的机器人”),自动扩展为包含起承转合的完整故事线。 风格迁移 (Style Adaptation):支持模仿特定导演风格(如“诺兰式非线性叙事”、“韦斯·安德森对称美学”)或特定 IP 语调进行剧本创作。
- 视觉增强与镜头预设 (Visual Enhancement) Prompt 友好型描述:在动作描写中自动嵌入关键视觉元素(如“低角度仰拍”、“赛博朋克霓虹光效”、“慢动作特写”),为下游生成提供丰富语义。 角色/场景圣经 (Bible Generation):自动提取并维护主要角色的外貌特征、服装细节及核心场景的环境描述,确保全文一致性,并为 video-gen-agent 提供固定的 Reference Prompt。 分镜预标记:在剧本中自动标注建议的景别(全景/中景/特写)和运镜方式(推/拉/摇/移),直接辅助 video-shot-agent 进行分镜拆解。
- 逻辑与可行性校验 (Logic & Feasibility Check) AI 生成边界识别:内置 2026 年主流视频模型能力图谱,自动识别并修正超出当前技术边界的需求(如“长达 1 分钟的无剪辑复杂长镜头”),提供替代性拍摄方案。 连贯性检查:检测时间线冲突、角色行为逻辑矛盾及场景转换突兀问题,确保叙事流畅。 合规预扫描:初步筛查剧本中的敏感内容、版权风险及伦理问题,提前预警,减轻 video-audit-agent 的后期压力。
- 格式化输出与对接 (Structured Output) 行业标准格式:支持输出 PDF (Final Draft 风格)、Fountain、CSV 等多种格式。 JSON 结构化数据:直接输出机器可读的 JSON 对象,包含场景 ID、角色列表、道具清单、环境标签及对应的 Prompt 片段,无缝对接 video-shot-agent。 版本管理:支持多版本剧本迭代,记录修改轨迹,方便团队协同与回溯。 🛠️ 技术架构亮点 叙事图谱推理 (Narrative Graph Reasoning):利用知识图谱技术构建人物关系与情节因果链,确保长篇故事的逻辑严密性。 多智能体协作写作:内部模拟“主编 - 编剧 - 审校”多角色协作机制,自我迭代优化剧本质量。 动态反馈学习:根据 video-audit-agent 的驳回数据和 video-gen-agent 的生成效果,自动调整写作策略,越来越懂“什么样的剧本好拍”。 📦 适用场景 AI 短剧/电影开发:快速生成高质量剧本原型,缩短前期策划周期。 营销广告创意:根据产品卖点,瞬间生成多个不同风格的广告脚本供选择。 互动叙事游戏:生成分支剧情树,为互动视频提供丰富的内容库。 教育/培训视频:将枯燥的知识文档转化为生动的情景剧剧本。 video-script-agent —— 让创意不再停留在脑海,是您构建专业化、工业化AIGC 视频生产线的第一块基石。 生态定位: video-script-agent (大脑:构思) ➡️ video-shot-agent (规划:拆解) ➡️ video-gen-agent (双手:创造) ➡️ video-audit-agent (眼睛:把关)
Metadata
Release files for penplot 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| penplot-0.1.0.tar.gz | 9.0 kB | With provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| penplot-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 17.8 kB
Release files / penplot-0.1.0.tar.gz
| Download URL | penplot-0.1.0.tar.gz |
|---|---|
| Size | 9.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
3b8ea9e221ddd6f200c8aecc01f7c30308f2b4fb1291c88dbe5487cea045bb2e
|
|
BLAKE2b-256 checksum How to use checksums |
e75dd7177149991a345fa92e3d959b41c590e0c73aad2365dbeb61d713d58208
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Aug 31, 2026.
Transparency logRelease files / penplot-0.1.0-py3-none-any.whl
| Download URL | penplot-0.1.0-py3-none-any.whl |
|---|---|
| Size | 8.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
ba98838b80c037a08bf7f4d4844bdb519fc66c6a01b0d9c682c1b273051e23f4
|
|
BLAKE2b-256 checksum How to use checksums |
15609d551ea5f77acfb149a38bd74e860ea9d6d5714a3fd60a5459266e00ecbb
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Aug 31, 2026.
Transparency logSecurity for penplot 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for penplot-0.1.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Aug 31, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.