Skip to main content

Anime Prompt Kit

Build editable anime character prompts from structured fields. Includes 12 original character concepts and dependency-free JavaScript and Python composers.

Made for use with AI Anime Generator or your preferred image generator. This toolkit assembles text locally; it does not generate images or call an API.

Python package

Requires Python 3.9 or later. Install from PyPI:

python -m pip install anime-prompt-kit
anime-prompt-kit --list
anime-prompt-kit sky-courier --setting "a snowy train station"
python -m anime_prompt_kit moon-librarian
from anime_prompt_kit import compose_prompt, from_template, list_templates

print(from_template("sky-courier", setting="a snowy train station"))
print(compose_prompt(subject="adult explorer", setting="forest"))

The Python API and CLI run locally without dependencies, accounts or API keys. Documentation and project overview.

JavaScript quick start

Requires Node.js 20 or later. No dependencies, account, or API key required.

git clone https://github.com/diaozxin007/anime-prompt-kit.git
cd anime-prompt-kit
node cli.js --list
node cli.js sky-courier
node cli.js sky-courier --setting "a snowy train station" --composition "full body character sheet"

Example output from node cli.js sky-courier:

adult courier with short silver hair and amber eyes, navy flight jacket and brass goggles, holding a folded map, floating harbor at sunrise, anime illustration, clean line art, soft cel shading, soft cinematic lighting, three-quarter portrait

Copy the output into AI Anime Generator to generate an image. The website is a separate service with its own account, credit, and usage terms; running this kit is free.

Use in JavaScript

import { composePrompt, fromTemplate } from './index.js';

console.log(fromTemplate('moon-librarian', {
  action: 'reading beside a window',
  lighting: 'warm candlelight',
}));

console.log(composePrompt({
  subject: 'adult explorer with dark curls and green eyes',
  outfit: 'teal coat and leather satchel',
  setting: 'a floating botanical garden',
  style: 'anime illustration, soft cel shading',
}));

Supported fields are subject, outfit, action, setting, style, lighting, and composition. Empty fields are omitted. Overrides replace the corresponding field without changing the stored template. Unknown template IDs and non-string field values throw an error.

This project is currently distributed through GitHub; no npm install is required.

Character templates

ID Concept
sky-courier Sky courier
forest-botanist Forest botanist
moon-librarian Moon librarian
desert-mechanic Desert mechanic
rain-detective Rain detective
tea-alchemist Tea alchemist
snow-ranger Snow ranger
ocean-cartographer Ocean cartographer
rooftop-musician Rooftop musician
garden-guardian Garden guardian
star-engineer Star engineer
village-baker Village baker

The canonical templates live in templates.json, so you can also copy and edit them without using JavaScript.

Keep a character recognizable

  1. Keep the subject and signature outfit fixed between prompts.
  2. Change one field at a time, such as action or setting.
  3. Keep a record of the model and settings used in your image generator.
  4. Where supported, use the same reference image to guide later generations.

These are text starting points, not a guarantee of character consistency. Different models interpret prompts differently. The included templates have not been individually image-tested; no generated results or performance claims are implied.

Python distribution data is copied from templates.json; the parity test checks both copies and all 12 JavaScript/Python outputs. Update both JSON files when adding templates.

Privacy

The composer and CLI run locally. They have no network calls, tracking, or credentials. Following a website link opens a separate external service.

Development and contributions

npm test
PYTHONPATH=python python3 -m unittest discover -s tests -v

Contributions are welcome: add original templates, improve examples, or report bugs through GitHub issues. Include the exact command and Node.js version for bug reports. Keep secrets and private prompts out of issues. Please use original character concepts and do not contribute copyrighted artwork or copied prompt collections.

License

MIT, covering the code and included template text.

Metadata

Release files for anime-prompt-kit 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for anime-prompt-kit 0.1.0
File Size Uploaded Provenance
anime_prompt_kit-0.1.0.tar.gz 10.8 kB With provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for anime-prompt-kit 0.1.0
File Interpreter ABI Platform
anime_prompt_kit-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 18.4 kB

Release files / anime_prompt_kit-0.1.0.tar.gz

Download URL anime_prompt_kit-0.1.0.tar.gz
Size 10.8 kB
Tags Source
SHA-256 checksum
How to use checksums
06ca969049b8cff9527d531275ee641996ae41074b83cb55dd415c377cfe13af
BLAKE2b-256 checksum
How to use checksums
18c0747216126216eb2c3236fa811806d489bd487a192c83edc23ba711e009af
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 Oct 20, 2026.

Transparency log

Release files / anime_prompt_kit-0.1.0-py3-none-any.whl

Download URL anime_prompt_kit-0.1.0-py3-none-any.whl
Size 7.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
891bbc406f89d1306bcae2fcc4a8e39419ad81cedc6fb14261ea3d3ef2ba1a19
BLAKE2b-256 checksum
How to use checksums
accce3ea9b7e575224ab2b02454aec970b061d843451858c83110faa043fffad
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 Oct 20, 2026.

Transparency log

Security for anime-prompt-kit 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.

Select from 2 files

Attestation for anime_prompt_kit-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 Oct 20, 2026.

Transparency log

A 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.

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files Full provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page