make-an-anime — плагин для Claude Code: аниме из истории
make-an-anime — плагин для Claude Code, который превращает историю в аниме со сценами, озвучкой и титрами. Запускается по запросу создать сцену или эпизод.
MIT ★ 152 обновлён 2026-11-08
/plugin marketplace add makevoid/claude-make-an-anime
/plugin install make-an-anime@make-an-animeЧто делает make-an-anime
Плагин разбивает историю на план производства: персонажей, голоса, список кадров и запросы для генерации. После подтверждения он создаёт материалы по этапам, проверяет результат и повторно генерирует кадры, которые не прошли проверку. Отдельные шаги можно запускать командами ruby mv.rb, а файлы сохраняются в output/<run>/.
Для генерации нужен ключ Fal и аккаунт с кредитом: платные запросы идут через Fal. На компьютере также нужны Ruby 3.2+ и Bundler, FFmpeg, ImageMagick, Python 3, Node.js 22.12+ и Chrome. Для необязательной обработки VFX нужны macOS 14+ и Swift 5.9+. Плагин спрашивает ключ Fal и хранит его как секретную настройку.
Какие задачи решает
- превратить историю в план сцен и кадров
- создать персонажей, озвучку и музыкальную дорожку для аниме
- наложить титры, субтитры и звуковые эффекты на сцены
- добавить к видео эффекты через Swift Core Image
Примеры запросов агенту
- Создай короткую аниме-сцену по истории в
story.md. - Сделай пилот из
story.md, используя фотографии персонажей из./refs. - Подготовь аниме-сцену и попроси меня утвердить план до платной генерации.
Как установить make-an-anime
Через маркетплейс плагинов
/plugin marketplace add makevoid/claude-make-an-anime/plugin install make-an-anime@make-an-animeПо шагам, с командами для каждой платформы: Плагины Claude Code: маркетплейсы, установка и как собрать свой
Вопросы о make-an-anime
Как установить make-an-anime в Claude Code?
Выполни команды по порядку: /plugin marketplace add makevoid/claude-make-an-anime, затем /plugin install make-an-anime@make-an-anime.
Что делает make-an-anime?
Плагин превращает историю в аниме: планирует персонажей и кадры, создаёт изображения, видео, голоса, музыку, титры и звуковые эффекты. Перед платной генерацией он запрашивает подтверждение плана.
Что нужно для работы make-an-anime?
Нужны ключ Fal и аккаунт Fal с кредитом, Ruby 3.2+ и Bundler, FFmpeg, ImageMagick, Python 3, Node.js 22.12+ и Chrome. Для необязательной обработки VFX требуются macOS 14+ и Swift 5.9+.
Исходный текст
SKILL.md · MIT
# Make an Anime
A Claude Code plugin that turns a story into a finished anime: character sheets, camera-directed shots, voices, a score, titles, subtitles, sound effects and finishing VFX. It works at any length, from a 12-second scene to a full episode.
<img src="https://github.com/user-attachments/assets/64abaa31-71bf-4c0e-ae8e-99db67edc366" alt="Four frames, one from each example: two friends by a vending machine, a scientist and his assistant in a lab, a Muay Thai fighter against a karate fighter at sunset, and a grandmother and granddaughter in an omelette shop" width="100%">
## Examples
All four were made with the plugin, with Japanese voices and English subtitles, and they show how far the same steps can stretch. Sound on.
### The Last One: slice of life, 12 s
Two university friends have just missed the last train home. Across the rice fields it shrinks into the distance, and the only question left is what to get from the vending machine.
https://github.com/user-attachments/assets/4be1633c-94f1-4c79-97c5-e8a69d96edc2
### The Invention of the Century: comedy, 20 s
A theatrical scientist unveils a shrinking fluid in his cramped lab. His deadpan assistant thinks it's melon soda, and then she eats the evidence.
https://github.com/user-attachments/assets/7ec2cd36-a097-406c-b1a9-072a2deb27ed
### One Round at the River: fight, 17 s
A cocky Muay Thai fighter challenges a calm karate man to one fight on a riverbank at sunset, with hard hand-to-hand contact and no superpowers.
https://github.com/user-attachments/assets/9be8bfb9-86dc-4d77-ba8d-c2e7a2b92733
### Too Salty: cooking drama, 74 s
For 91 days, Hana has tried to make her grandmother's rolled omelette, and every morning she hears the same verdict. Then one morning she leaves out the salt. This is the longest of the four, a whole short story told in 19 shots, painted with GPT Image 2.6.
https://github.com/user-attachments/assets/352d902c-39b4-4511-8496-56b03737c028
The toolkit also works at full length: it was first used for a narrated anime documentary of over 12 minutes, in about 40 scenes. See [Full episodes](#full-episodes).
## Installation
In Claude Code:
```text
/plugin marketplace add makevoid/claude-make-an-anime
/plugin install make-an-anime@make-an-anime
```
The plugin asks for your [Fal](https://fal.ai) API key and stores it as a sensitive option. All paid generation goes through Fal, so you need an account with credit.
You also need these on your machine:
| Tool | Used for |
| --- | --- |
| Ruby 3.2+ and Bundler | The toolkit itself |
| FFmpeg, ImageMagick | Video, audio and image work |
| Python 3 | Green-screen keying, score editing, analysis |
| Node.js 22.12+ and Chrome | Rendering p5 titles, subtitles and composites |
| macOS 14+ and Swift 5.9+ | Optional: the Core Image VFX pass |
Each project installs its own Ruby, Node and Python packages when the skill runs `setup`, and `doctor` reports anything missing.
## Usage
Ask Claude for what you want:
```text
/make-an-anime Make a 2-minute pilot from story.md, with characters based on the photos in ./refs
```
Claude reads the story, writes a production plan (cast, voices, shot list, every prompt, the number of paid calls) and asks you to approve it. No paid call runs before that approval. It then produces and reviews each step, and retakes shots that fail review.
Reference photos are optional: original characters are designed from text. Use photos of real people only with their consent.
MiniMax H3 remains the default video model. Ask explicitly for **Seedance** to use Seedance 2.5 US, defaulting to **480p** unless you specify another resolution. It supports image-to-video, reference-to-video and optional draft completion at 1080p. See [Seedance settings and drafts](skills/make-an-anime/references/seedance.md).
## How a scene is made
Each stage reads prompts from `prompts/<run>/` and writes to `output/<run>/`, so everything can be inspected and redone on its own.
<img src="https://github.com/user-attachments/assets/56267103-9aec-4482-a20b-f4c1d074eb2a" alt="One shot of Too Salty at four stages: the character sheet, the painted keyframe, a frame of the animated take, and the finished frame with subtitles" width="100%">
1. **Character and location sheets.** A style bible (`config/style.md`) guides the image prompts, so the whole cast shares one look. GPT Image 2.6 draws a sheet for each character and location, and those sheets become the references for everything after.
2. **Voices and score.** Each character gets one ElevenLabs voice in `config/cast.yml`. Voices come before animation because line lengths decide shot lengths. ElevenLabs Music then composes one score, and `gen:mix` ducks it under the voices.
3. **Keyframes.** GPT Image 2.6 paints the first frame of each shot from the sheets.
4. **Shots.** MiniMax H3 animates each keyframe as one continuous take, with the camera move written into the prompt and the speaker's voice as target audio so the mouth follows the line. Held stills and colour inserts cost nothing. Existing takes can be reused across scenes with `from_take`. For moments that need exact placement, [layered scenes](skills/make-an-anime/references/layered-scenes.md) composite green-screen sprites over a painted plate.
5. **Overlay.** A p5 script (`05_overlay.js`) draws titles, subtitles, fades and any composite work.
6. **Sound.** `sfx:gen` creates sound effects with ElevenLabs Sound Effects v3, and `sfx:mix` places them from a cue list and levels them against the mix.
7. **Finish.** `vfx:render` adds grain, glow or impact effects with Swift Core Image, on frame-accurate cues. The optional `vfx:bake` pass preserves the plain picture so repeating the finish does not accumulate effects.
For detailed staging and playback review, see [Staging and review](skills/make-an-anime/references/staging-and-review.md). Local graphics tools include [deterministic particles and light-only glow](skills/make-an-anime/references/particles-and-glow.md), plus [animation asset preparation](skills/make-an-anime/references/animation-assets.md).
The same steps as commands, once a project and its prompts exist:
```sh
export RUN=my-scene
ruby mv.rb gen:dialogue
ruby mv.rb gen:music
ruby mv.rb gen:mix
ruby mv.rb gen:keyframes
ruby mv.rb gen:shots
ruby mv.rb gen:overlay
SFX=my-scene-sfx ruby mv.rb sfx:gen
SFX=my-scene-sfx ruby mv.rb sfx:mix
ruby mv.rb vfx:build
VFX=my-scene-vfx ruby mv.rb vfx:render # -> output/my-scene/final_vfx.mp4
```
Check current prices on Fal before you run anything. For scale, the first build of *Too Salty*, made with GPT Image 2.5, took 4 sheets, 22 keyframe images, 23 H3 takes, about 22 voice takes, 1 score and 9 sound effects, retakes included.
## How a scene is edited
Everything is a file and every step is cached, so a change only redoes what it affects. Replaced takes are kept in `output/<run>/rejected/`. These are real edits from the examples:
| What was wrong | The edit | Cost |
| --- | --- | --- |
| Two voice lines overlapped | Changed `at:` in `03_dialogue.yml`, then `gen:dialogue` and `gen:mix` reused the takes | Free |
| A voice take said its word twice | Added `gate_s` to mute the first one | Free |
| A tear ran down Hana's cheek | Repainted the keyframe and changed the prompt, then `ONLY=outburst FORCE=1` on `gen:keyframes` and `gen:shots` | 1 image and 1 H3 take per try |
| An umbrella vanished from the background mid-shot | Painted an end frame that keeps it, and set `end_image` on the shot | 1 image and 1 H3 take per try |
| Steam washed out a tray of omelettes | Replaced the take with a slowly zooming still of its keyframe | Free |
A retake needs a changed prompt. Fal requests are stored as receipts by their exact input, so `FORCE=1` with an unchanged prompt fetches the same result again, at no charge.
Local review tools help decide what to retake:
| Command | What it shows |
| --- | --- |
| `review:camera` | The camera move each shot made, with frame strips to read by eye |
| `review:dialogue` | What Whisper heard in each take (paid) |
| `dialogue:timeline` | Lines against shots and cuts |
| `audio:seams` | Abrupt music changes at scene joins and inside a score |
## Full episodes
A longer project uses the same steps, one run per scene, plus:
- `scene:new[ep01-s05,480]` to scaffold a scene, with one config file per scene so several agents can work at once
- `config/episodes/ep01.yml` for the playing order
- `episode:preview` to join scenes, levelling the voices across them (`VOICE_DB`) and fading the seams (`SEAMS=1`)
- production waves with sub-agents (`work:next`, `work:accept`), starting with the opening and the emotional peak
[full-episode.md](skills/make-an-anime/references/full-episode.md) has the complete workflow.
## Repository layout
```text
.claude-plugin/ plugin and marketplace manifests
skills/make-an-anime/
SKILL.md what Claude follows
references/ planning, prompts, camera language, audio, episodes
examples/ workflow showcases only: 01 is read on every run; 02-04 are three of the films above
scripts/
mv.rb, mcp.rb CLI and MCP entry points
lib/fal/ Fal queue client with receipts, and model wrappers
lib/pipeline/steps/ RefBase, Dialogue, Music, Mix, Keyframes, Shots, Clips, Overlay
lib/media/, lib/toolkit/ FFmpeg, ImageMagick, Python, p5 and Swift wrappers; project tools
tools/p5/ headless renderer and the Anim library
tools/python/ keying, tracking, analysis, score editing
tools/vfx/ Swift Core Image renderer
spec/ RSpec suite
```
The specs never call Fal unless you authorize the live spec. They run from `skills/make-an-anime/scripts` after `npm ci`, with `MV_PYTHON` pointing at a Python that has `requirements.txt` installed:
```sh
bundle exec rspec --tag core
bundle exec rspec --tag media # includes a whole scene with synthetic media
```
## Bonus: behind the scenes
Everything here comes from the four examples above, plus one extra film at the end: what the skill generated, what got thrown away, and what changed on the way to the finished film. The demo videos show the first build of *Too Salty*, made with GPT Image 2.5. Its sheets, keyframes and frame strips further down come from the current GPT Image 2.6 version.
### Demo videos
**Raw MiniMax H3 takes.** 18 takes straight from the model, with no subtitles, grading or sound.
https://github.com/user-attachments/assets/49479813-9511-44c2-94a1-74e501aab90e
**One shot, three stages.** One shot from each anime, first as the painted keyframe, then as the silent H3 take, then finished with sound on.
https://github.com/user-attachments/assets/11ecdaf9-3d56-4855-bff2-ddfa5c6a423b
**Rejected takes next to the kept ones.** Seven real retakes and what fixed each one. Silent.
https://github.com/user-attachments/assets/3b14dde3-efe6-40db-9787-b4cd3c1998c6
**The same scene in two languages.** *The Last One* was made in English first, then voiced again in Japanese with English subtitles.
https://github.com/user-attachments/assets/638400e6-5f41-445d-b2cd-281a6d3dcd3b
### Character sheets
The image model draws a turnaround and expressions for each character. Every later image and take uses these sheets as references, which keeps the characters on-model from shot to shot.
**The Last One:** Mio and Haru
<img src="https://github.com/user-attachments/assets/393854b4-920c-4ffe-819e-737e72e83852" alt="Character sheet of Mio: glasses, yellow shirt, green skirt and backpack" width="49%"> <img src="https://github.com/user-attachments/assets/06372093-7d9c-4ad3-b32a-afd188aab3ad" alt="Character sheet of Haru" width="49%">
**The Invention of the Century:** the scientist and Aoi
<img src="https://github.com/user-attachments/assets/b9a655d9-c7d8-42ae-82d6-87222034c8ba" alt="Character sheet of the scientist: lab coat, red shirt, goggles on his head" width="49%"> <img src="https://github.com/user-attachments/assets/8a2996e9-67fb-470b-a26c-62d1ca1d6f5e" alt="Character sheet of Aoi: blue hair, glasses, lab coat over a hoodie" width="49%">
**One Round at the River:** Riku and Ren
<img src="https://github.com/user-attachments/assets/7eed18cb-58e7-4b19-ab1d-f09c2e069471" alt="Character sheet of Riku: black tank top, red Muay Thai shorts, hand wraps" width="49%"> <img src="https://github.com/user-attachments/assets/516f64db-8007-4393-b168-86a0d5a55cc0" alt="Character sheet of Ren: white karate gi with a black belt" width="49%">
**Too Salty:** Hana and Kiku
<img src="https://github.com/user-attachments/assets/1e6e2e40-ac07-451b-9c64-043af4ec34eb" alt="Character sheet of Hana: headscarf, pale shirt, dark apron" width="49%"> <img src="https://github.com/user-attachments/assets/3b4aecd5-cc08-4334-b3d9-4477ce7df923" alt="Character sheet of Kiku: elderly woman in a dark top and white apron" width="49%">
A character is cheapest to change at this stage. The scientist went through three sheets, and the shots made from an earlier one were redone from the last:
<img src="https://github.com/user-attachments/assets/62f2630a-df25-4e3f-94ad-b57e2ab9e56a" alt="Three versions of the scientist's character sheet, from scruffy and grimy to clean-cut" width="100%">
### Location sheets
Locations get sheets too, so a place stays the same from one shot to the next.
<img src="https://github.com/user-attachments/assets/565919ba-b12e-4bd3-9117-65774cb51f87" alt="A country road through rice fields below green mountains" width="49%"> <img src="https://github.com/user-attachments/assets/ec803261-e7e2-4a7b-bdf8-b78cf6e224e8" alt="A cramped laboratory at night, full of shelves and glassware" width="49%">
<img src="https://github.com/user-attachments/assets/6277c2a2-b512-4729-8fd0-bb685dee4cc9" alt="A grassy riverbank and an iron bridge at sunset" width="49%"> <img src="https://github.com/user-attachments/assets/29fbd1ee-b326-4ce0-be8a-3d0d92bb801e" alt="A small omelette shop at night, with a counter and a copper pan" width="49%">
<img src="https://github.com/user-attachments/assets/e779296a-3330-4943-84ea-33e3a8890873" alt="A narrow old shopping street, wet from the rain" width="49%">
### Keyframes
Each shot starts from one painted frame. These are the keyframes of all four anime.
**The Last One**
<img src="https://github.com/user-attachments/assets/f42fc8f2-0c2a-4f36-9c53-179303b68066" alt="Three keyframes of The Last One" width="100%">
**The Invention of the Century**
<img src="https://github.com/user-attachments/assets/dd970f7a-2304-4be4-af07-ff6ca2cfd968" alt="Eight keyframes of The Invention of the Century" width="100%">
**One Round at the River**
<img src="https://github.com/user-attachments/assets/546e9c99-ff5b-4bab-911d-2740d1d8f0fb" alt="Nine keyframes of One Round at the River" width="100%">
**Too Salty**
<img src="https://github.com/user-attachments/assets/1a1eaaaf-d996-4571-8ed6-2ac98ded358d" alt="Sixteen keyframes of Too Salty" width="100%">
### MiniMax H3 takes, frame by frame
Five frames across each continuous take, in order.
Two characters act at once: he keeps talking while she eats the evidence.
<img src="https://github.com/user-attachments/assets/3a921bc3-563a-4296-bdeb-71f541d0214b" alt="Five frames of the scientist talking while Aoi eats a tiny pineapple with tweezers" width="100%">
A start frame and an end frame are both painted, and H3 animates the change between them.
<img src="https://github.com/user-attachments/assets/7fb99f31-9e81-4f63-85fe-c1cd1c38a534" alt="Five frames of a pineapple shrinking to almost nothing under a dropper" width="100%">
The camera moves around the fighters as they trade blows.
<img src="https://github.com/user-attachments/assets/ca108e6b-47a4-4939-a774-61d39bb3a0d4" alt="Five frames of the two fighters exchanging punches while the camera circles them" width="100%">
The lips follow a whispered line, and the two hands stay on the pan.
<img src="https://github.com/user-attachments/assets/ac3f6781-0cdc-483b-90ab-8e2c6f37f239" alt="Five frames of Kiku and Hana with their eyes closed over a pan, Kiku whispering" width="100%">
Cooking is the hard part to animate: the omelette has to roll as one piece.
<img src="https://github.com/user-attachments/assets/48ea195a-4450-4fc9-bd9e-ff3df002a239" alt="Five frames of a rolled omelette being pushed along a copper pan" width="100%">
A wide shot with a small action: the shop curtain goes up at dawn.
<img src="https://github.com/user-attachments/assets/6ceafd23-827e-4d51-af26-2f24335d6364" alt="Five frames of Hana hanging the curtain over the shop door on a wet street" width="100%">
### Editing takes together
The first two frames come from separate H3 takes, and the last is the finished split panel, cut together in p5 with the subtitle on top.
<img src="https://github.com/user-attachments/assets/e1db381d-0eff-4e29-88a3-7c7904dfc2b1" alt="A frame of Riku, a frame of Ren, and the finished split panel of the two with a subtitle" width="100%">
### One more film: Final Inspection
A rusted 40-metre robot is due to be cut up tomorrow. Tetsu, the old mechanic who kept it running for 30 years, climbs up for one last check and shares a thermos of tea with it. 34 s, painted with GPT Image 2.6.
https://github.com/user-attachments/assets/b91a89cc-f32b-46f3-95ac-fcf6d19f8e58
## License
[MIT](LICENSE)
© makevoid · MIT · makevoid/claude-make-an-anime