Ae Blender Frame Recreation logo

Ae Blender Frame Recreation

Community
EGSECDA
ae-blender-frame-recreation

根据参考视频逐帧拆解并制作可编辑的 After Effects 动效工程,结合图像模型生成素材、Blender 三维场景与运镜,复刻短帧 MG、UI 和三维文字;适用于参考复刻、主题改编及已有成片的视觉返修。

Overview

PublisherEGSECDA
Repositoryae-blender-frame-recreation
Skill nameae-blender-frame-recreation
Stars
50
Forks
3
Bundled files
20
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 20 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by EGSECDA on GitHub. Read the source before you install it.

Installation

Install the Ae Blender Frame Recreation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/EGSECDA/ae-blender-frame-recreation/tree/main
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/EGSECDA/ae-blender-frame-recreation.git \
  .claude/skills/ae-blender-frame-recreation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ae Blender Frame Recreation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ae Blender Frame Recreation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ae Blender Frame Recreation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

AE / Blender 逐帧视觉复刻

交付能继续编辑的 AE 工程、必要的 Blender 源文件、完整素材和经过验证的成片。先分清参考的节奏、图形语言、空间运动和可替换的题材;保留用户选定的软件与改编范围。

接手现有项目

先找实际输入视频、最新 AEP、生成脚本、素材清单、已导出版本和用户指出的帧。读取最新交付记录并验证文件存在,不能仅凭文件名的 FINAL / V3 判断版本。保护当前未保存的应用会话,脚本构建和后台渲染优先使用独立进程与唯一候选文件。

确认帧率、时长、画幅、音轨、主题、必要角色及输出目录。能从现有工程或用户上下文确定的事项直接沿用。素材、缓存、工程、渲染和审核证据分别放入项目子目录;运行环境与工具路径现场发现,不沿用他人机器的绝对路径。

按需要读取

  • 参考拆解、连续帧提取、版本差异和编码检查:读 frame-review.md,使用 scripts/frame_review.py。
  • 原生 AE 编程、文字、人物框、三维图层、保存和渲染:读 ae-engineering.md,按需载入 scripts/ae_primitives.jsx。
  • 真实近中远景、纸张材质、镜头景深、透明序列:读 blender-depth.md。scripts/blender_paper_demo.py 是可编辑的最小演示,按用户场景重建布局。
  • 素材生成和设计判断:读 visual-direction.md。
  • 最终文件、版本冻结和故障处理:读 delivery.md。

工作循环

  1. 逐帧建账。 对参考的相关区段提取全部帧,记录镜头区间和内部 1–6 帧事件;完整复刻时覆盖整片。以整数帧保存事件,秒数用于显示。分别记录预备、冲击、过冲、落定、保持、退出,不用平滑长补间替代短促切换。示例结构见 example_timeline.json,其数值仅是演示。
  2. 先明确构图。 给脸部、主要动作、标题、辅助文字和景深物体分配空间;设计明确的阅读优先级。人物、前景和文字可以有经过设计的遮挡,但脸和需要读完的文字应有完整可读阶段。将用户截图中的问题定位到连续帧范围,检查是否影响同类段落。
  3. 分别制作。 图像模型负责角色原画、环境画、材质等位图;可编辑 UI、可读文字、蒙版和 MG 在 AE 中制作;真实场景几何、物体深度、相机运动和景深在 Blender 中制作。生成图片不能代替用户要求的真实三维运镜。
  4. 分阶段原生渲染。 先做短测试确认字体、抠像、Alpha、模糊角度和时间映射,再制作全段。文字进场、角色框、对白、三维字和高潮分别检查;必要时并行分段审核,但整合工程只由一个写入者串行保存。
  5. 看实际输出再修。 修改关键帧或图层后,保存唯一候选,关闭重开核对关键参数,再从这个明确路径渲染。检查连续帧与正常速度播放各自能发现的问题,记录真正看过的范围。已有错误不能由“脚本 SUCCESS”关闭。
  6. 冻结并交付。 改动帧全部复看;只有像素或有效参数未变的区段才能沿用旧检查结论。完成原生工程检查、最终编码全片解码及音轨验证,整理正式入口和逐帧证据。不要把审核中间件冒充成片,也不要用“100% 信心”代替可核验结果。

三个容易做错的决定

  • 对话是一个共同场景。 多角色对话保持各自固定站位;发言状态控制彩色/灰色、亮度和轻微动作,避免靠每次替换同一个角色图层改变站位。左右安排服从当前用户要求。
  • 固定框与内部取景分开。 用窗口预合成裁切人物,外层移动窗口,内层移动/缩放原画。逐帧检查脸的实际位置,不能只检查图层中心或最终姿态。
  • 高潮先有组织,再打破组织。 例如规则符纸阵先聚集和短暂停顿,再在几帧内向镜头爆散,随后大幅减速。近景尺寸、虚焦、曲率、遮挡和中景清晰纹理共同表现深度;单纯增加平面图形数量只会加乱。

完成判断

用户指定的效果和修正已进入实际渲染;角色与关键文字在可读阶段清楚;短帧转场无意外跳动、空帧或蒙版泄漏;三维物体有真实深度且材质在交付分辨率下可辨;素材无丢失、表达式无错误、音轨和总帧数正确。对无法控制的窗口或未验证的项目如实说明,保持已有文件可用。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Ae Blender Frame Recreation AI skill do?

根据参考视频逐帧拆解并制作可编辑的 After Effects 动效工程,结合图像模型生成素材、Blender 三维场景与运镜,复刻短帧 MG、UI 和三维文字;适用于参考复刻、主题改编及已有成片的视觉返修。

Why use Ae Blender Frame Recreation on TypingMind?

Because you install it once and use it with any model. Ae Blender Frame Recreation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ae Blender Frame Recreation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/EGSECDA/ae-blender-frame-recreation/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Ae Blender Frame Recreation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ae Blender Frame Recreation?

As many as you like. As long as a model supports skills, you can use Ae Blender Frame Recreation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ae Blender Frame Recreation AI skill free?

It is published on GitHub by EGSECDA. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇