LT

l-trunks/ai-film-skills

开发工具

本页由 AI 翻译,技术细节请以原文为准。 查看原文

29 stars 质量 53 趋势 20NOASSERTION

本地 AI 短片生产线 技能套件 —— 一张 12GB 显卡跑通 LTX / Wan / MiniMax H3,含 1600+ 行踩坑经验与防同质化机制

概览

——六个克劳德技能,关于决定什么,而不是如何安装东西。 最简单的路径——把这个粘贴到 Claude Code:“为我安装这个技能:https://github.com/L-Trunks/ai-film-skills —— 克隆它并运行 install.sh” 然后说“做一个短片。”这个技能本身就是方法论和知识;它依赖于没有脚本、模型或 GPU。要运行参考实现,先在示例/脚本/config.py 中设置三条路径,并运行 Python doctor.py。 四部电影,全部用一个。生成路径中没有云API。 下面的片段是无声动图。:▶狱卒 ·镜子——钟楼下 ·镜子——屋顶 ·九尾 ·单海 两集,40和34个镜头,每集1分47秒。模型的本地对口型对话,后期重新配音:同一个角色在四十个镜头后仍是同一个角色,台词必须对齐。

概述(AI 翻译)

本地生成AI短片导演知识库——六项Claude技能关于该决定什么,而不是如何安装东西。

中文 ·画廊 ·两种技能 ·MiniMax H3 在 12 GB 上 ·署名

安装它就能正常工作了。 最简单的路径——把这个粘贴到 Claude Code: “帮我安装这个技能:https://github.com/L-Trunks/ai-film-skills ——克隆它并运行 install.sh” 那就说“拍一部短片”。技能本身就是方法论和知识;它依赖于没有剧本、没有模型、没有GPU的。

要运行参考实现,请在examples/scripts/config.py设置三条路径。 并先跑python doctor.py。


先看

四部电影,全部用一台**RTX 4070 Ti(12GB)**制作。生成路径中没有云API。

以下片段为无声GIF。带声音的完整版: ▶ 狱卒·镜子——钟楼下 · 镜子——屋顶·九尾· 山海

狱卒 — 长镜头、带有对白的剧集剧

▶ 48秒片段,带声音 — 第1至2集,1分34秒至2分22秒。

两集,40和34个镜头,每集1分47秒。模特本地对口型对白, 后期重新配音。

本页由 AI 翻译,技术细节请以原文为准。

README

以下为原文 README 节选,完整内容请查看原文。

ai-film-skills

A directing knowledge base for locally-generated AI short films — six Claude Skills about what to decide, not how to install things.

中文 · Gallery · Two kinds of skill · MiniMax H3 on 12 GB · Attribution

Install it and it works. Easiest path — paste this at Claude Code: “Install this skill for me: https://github.com/L-Trunks/ai-film-skills — clone it and run install.sh” Then say “make a short film.” The skill itself is methodology and knowledge; it depends on no scripts, no models, no GPU.

To run the reference implementations too, set three paths in examples/scripts/config.py and run python doctor.py first.


Watch first

Four films, all produced on one RTX 4070 Ti (12 GB). No cloud API in the generation path.

The clips below are silent GIFs. Full versions with sound: ▶ The Jailer · Mirror — Below the Clock Tower · Mirror — Rooftop · Nine Tails · Shan Hai

The Jailer — long-shot, episodic drama with dialogue

▶ 48-second clip, with sound — episodes 1–2, from 1’34" to 2’22".

Two episodes, 40 and 34 shots, 1’47" each. Native lip-synced dialogue from the model, re-voiced in post. This is the first one where the audience checks your work: the same character has to still be the same character forty shots later, and the lines have to line up.

It also overturned two of our own conclusions — that over-long prompts should be cut down, and that audio: BGM throughout was unbreakable. Both are written up in the gallery.

⚠️ Where this stops. We ran two more episodes and then called it: on a 12 GB card this pipeline makes films, not series. At 736×416 and ~7 min per 5-second shot, 68 shots is an overnight run for 1’45" of finished cut — and at 0.31 MP a face in a medium shot is 40–90 px, so 76% of character shots are forced to be close-ups. Episodic drama needs mid-shots to play scenes. Neither limit is a craft problem and neither goes away by picking a simpler art style — ours already was one. Everything below still holds on cloud APIs or bigger cards; see dialogue-drama.md for the full write-up.

Mirror — when the line above stops working, ship excerpts instead

▶ Below the Clock Tower, 33 seconds, with sound — 9 shots, 8 lines, two women in shot/reverse-shot.

▶ Rooftop, 14 seconds, with sound

在 GitHub 查看完整 README

推荐工具

换一个关键词,或者移除筛选条件。

安装

npx skillfish add l-trunks/ai-film-skills
新手?先看 mcpskill.org 教程 →