Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Open-Source AI Workflow Produces Two Whiteboard Animation Videos

AI summary

The Juejin AI article author says they used WorkBuddy to turn two narration scripts into an 83-second Long March route video and a 43-second Agent history video, both rendered at 1280×720 and 24fps. The seven-stage workflow synchronizes generated illustrations, handwriting, narration, subtitles, and camera movement, and is published as an MIT-licensed GitHub project containing 21 scripts, 28 tested parameters, examples, and an acceptance checklist. The author tested it on Windows 11 with Python 3.10 or later and FFmpeg, while noting that parameters may need adjustment on other systems.

In-depth insight

The repository provides concrete scripts and example artifacts for reproducing an end-to-end AI whiteboard-animation workflow, rather than offering only a conceptual demonstration.

先说清楚这类片子长什么样。笔尖走到哪,线稿长到哪;讲到瑞金,「瑞金」和「1934.10」跟着一笔一笔被写出来。镜头推近看细节,讲完再拉远,露出整张路线图,底下一行字幕稳稳跟着人声。

看着挺顺,做起来全是坑。白板动画难的不是把图画出来,是让笔、声音、字幕、镜头踩在同一条时间轴上。

自己手绘得会画画,用 AE 得逐帧打关键帧,让 AI 直接生成视频又管不住哪一笔在第几秒出现。所以常见的翻车长这样:手在动画面没东西,字幕已经出来了人声还没起,讲到第三站镜头还停在第一站。

我用 WorkBuddy 把两份解说稿跑成了两条成片:长征路线 83 秒,Agent 智能体发展史 43 秒,都是 1280×720、24fps。没有一张图是手画的,没有一帧是在剪辑软件里拖出来的,全靠一条固定产线跑完,七道工序、21 个脚本、28 条实测参数,已经开源到 GitHub。

这篇不聊过程里绕过的弯,只讲定稿版怎么跑:每一步喂什么进去、跑哪条命令、吐出来什么。

#WorkBuddy#srt-whiteboard-workflow#SeedAudio 1.0#faster-whisper#FFmpeg#srt-whiteboard-animation

Original · 9 min readRead the original
Group chat

No comments yet. Start the conversation.