comic-maker

Free plan LinuxSelf-hostedWindows

What comic-maker is

comic-maker is open-source software for turning a story idea into a lettered comic with locally run language and image models. A local Ollama chat model produces the title, characters, pages, and panel details; the resulting JSON can be edited by hand before image creation. ComfyUI with z-image turbo checkpoints generates an image for each panel, and the project lets users adapt the generation function to work with another model. A PIL compositor assembles the pages, with support for one to nine panels, diagonal gutters, speech bubbles with tails, Impact sound effects, and a title on the first page.

Creators can choose the built-in sunday-strip, manga, noir, and euro-album styles or provide a style description. Per-character seed families and repeated visual descriptions in panel prompts are intended to help keep characters consistent. The workflow separates script creation, panel generation, and assembly, so the JSON can be revised between stages. Exports include PNG pages and a CBZ archive. The project is MIT licensed and described as an early release under active development, with its API, prompts, and layouts subject to change. Its documented prerequisites are Python 3.10 or later with Pillow, Ollama with a chat model, and ComfyUI with z-image turbo checkpoints. It is designed for local use on one PC, without cloud services, credits, or accounts.

Who it suits

comic-maker suits comic creators who want a local workflow that takes a story idea through script, image generation, and page assembly. It is particularly relevant to people comfortable setting up Python, Ollama, and ComfyUI on Windows, Linux, or a self-hosted system.

What it does well

Runs locally without cloud services, credits, or accounts.
Lets users edit script JSON between workflow stages.
Composes pages with one to nine panels and multiple styles.
Exports PNG pages and CBZ archives.
MIT licensed and free to use.

What to know first

Requires Python, Ollama, and ComfyUI prerequisites.
Speech bubbles currently anchor at the top center.
The early-release API, prompts, and layouts may change.

Limits

The software is free and MIT licensed. The current speech bubbles anchor at the top center; character-aware placement and multi-character bubble tails are future work. Its API, prompts, and layouts may change as the early-release project develops.

Getting started

Open the comic-maker repository on GitHub.
Set up Python 3.10 or later with Pillow.
Install Ollama and provide a chat model.
Set up ComfyUI with z-image turbo checkpoints.
Run the script, panel-generation, and assembly stages separately if desired.
Edit the generated JSON between stages, then export PNG pages or a CBZ archive.

Verdict

Pick comic-maker if you want a free, local comic workflow and are comfortable configuring its model prerequisites. The script editing and page composition tools cover several stages, but creators who need more precise speech-bubble placement should note that bubbles currently anchor at the top center.

Questions

Does comic-maker cost anything?

It is free and open source under the MIT license.

Which platforms does it support?

The listed platforms are Linux, Windows, and self-hosted use.

Does it use cloud models or require an account?

The project describes its workflow as local, with no cloud, credits, or accounts.

What does comic-maker need to run?

Its quickstart lists Python 3.10 or later with Pillow, Ollama with a chat model, and ComfyUI with z-image turbo checkpoints.

What can it export?

The compositor produces PNG pages and a CBZ comic archive.

Can users change the comic style or image model?

Users can choose sunday-strip, manga, noir, euro-album, or provide a style description. The image-generation function can be edited to use another model.

Facts from comic-maker's own pages

Character consistency: The project uses a per-character seed family and repeats the character’s visual description in each panel prompt to help maintain consistency. · github.com, 8 Oct 2026
Development status: The project describes itself as an actively developing early release and says its API, prompts, and layouts may continue to change. · github.com, 8 Oct 2026
Export: The compositor produces PNG pages and a CBZ comic archive. · github.com, 8 Oct 2026
Features: Page assembly supports 1–9 panels per page, diagonal gutters, wrapped speech bubbles with tails, Impact sound effects, and a title on page one. · github.com, 8 Oct 2026
Image generation: ComfyUI with z-image turbo generates one image per panel, and the README says users can edit the generation function to use another model. · github.com, 8 Oct 2026
Integrations: The documented workflow uses Ollama for a chat model and ComfyUI with z-image turbo checkpoints for panel images. · github.com, 8 Oct 2026
Intended audience: The README says the project was made with local models on one PC. · github.com, 8 Oct 2026
Known limitation: Speech bubbles currently anchor at the top center; character-aware placement is listed on the roadmap. · github.com, 8 Oct 2026
Known limitations: The roadmap says speech bubbles currently anchor top-center and lists character-position-aware placement and multi-character bubble tails as future work. · github.com, 8 Oct 2026
License: The repository states that comic-maker is MIT licensed. · github.com, 8 Oct 2026
Local use: The README says the project uses local models on one PC and requires no cloud, credits, or accounts. · github.com, 8 Oct 2026
Page composition: The PIL compositor supports 1–9 panels per page, diagonal gutters, speech bubbles with tails, Impact sound effects, a title on page one, and CBZ export. · github.com, 8 Oct 2026
Privacy: The README describes the tool as fully local, with no cloud, credits, or accounts. · github.com, 8 Oct 2026
Purpose: Comic-maker turns a story idea into a lettered comic using a local language model, a local image model, and a compositor. · github.com, 8 Oct 2026
Requirements: The quickstart lists Python 3.10 or later with Pillow, Ollama with a chat model, and ComfyUI with z-image turbo checkpoints as prerequisites. · github.com, 8 Oct 2026
Script generation: A local Ollama model creates the title, characters, pages, and panel details, and users can edit the resulting JSON by hand. · github.com, 8 Oct 2026
Styles: Built-in styles are sunday-strip, manga, noir, and euro-album, and users can also provide a style description. · github.com, 8 Oct 2026
Support: The README invites users to follow the repository and submit issues and ideas. · github.com, 8 Oct 2026
Support and feedback: The README invites users to follow the repository and submit issues and ideas. · github.com, 8 Oct 2026
Workflow: Script, panel generation, and assembly can run as separate stages, with the script JSON editable between stages. · github.com, 8 Oct 2026

Where comic-maker stands on Freedom251

AI Comic Generators#8 of 27