Blokjutsu

A local, permissively licensed, open-source Mac app for generating and editing images from text prompts with the open-weight MOSS-Image model.

To use Blokjutsu, download it and start with the User's Guide. The rest of this page is for developers.

What it is

• A Mac app (PySide6/Qt) around MOSS-Image's diffusers pipeline, running on the Apple GPU through PyTorch's MPS backend: text to image, image to image, variations, inpainting, outpainting, cropping, and upscaling, with live previews and a scrolling history
• Describe image and Enhance prompt, written by MOSS-Image's own text encoder (Qwen3.5-9B) with its output layer re-attached
• Local: models are downloaded once, on request, from a separate process; the app itself runs with the Hugging Face libraries in offline mode and never goes online
• Open source all the way down: the app, MOSS-Image's code, and its weights are all under the Apache License 2.0, a permissive license

Requirements

• A Mac with Apple silicon (M1 or later) and macOS 12.3 or later
• 32 GB of memory or more; 48 GB or more is comfortable
• About 40 GB of free disk space, mostly for the model

Install

Disk image: the Download for Mac button above (1.0.0rc4, about 360 MB). Open it and drag Blokjutsu to Applications.

Terminal installer: installs a private Python with the tested library versions into ~/Library/Application Support/Blokjutsu.noindex/ and builds ~/Applications/Blokjutsu.app. Nothing else on the Mac is changed. Read it first if you like.

curl -LsSf https://formdo.github.io/blokjutsu/install.sh | sh

To uninstall the app it installed (keeping images, settings, and the model):

curl -LsSf https://formdo.github.io/blokjutsu/install.sh | sh -s -- --uninstall

From PyPI: Blokjutsu needs Python 3.10 or later; a virtual environment is strongly recommended. The exact library versions it was tested with are in constraints.txt, which pip can use with -c constraints.txt.

python3 -m venv .venv
source .venv/bin/activate
pip install blokjutsu
blokjutsu

Contributing

CONTRIBUTING.md covers setting up a development environment, running the tests, the design and modules, building the .dmg, and releasing. The User's Guide's Technical notes explain how each control works.

Built on MOSS-Image

Blokjutsu is an independent desktop front end for MOSS-Image, the text-to-image model and pipeline by the OpenMOSS Team and MOSI.AI. Blokjutsu is not affiliated with or endorsed by them. All of the image-making is theirs.

• Repository: https://github.com/OpenMOSS/MOSS-Image
• Technical report: https://arxiv.org/abs/2610.23374
• User guide: https://github.com/OpenMOSS/MOSS-Image/blob/main/USERGUIDE.md

If you use images or results from Blokjutsu in research, please cite MOSS-Image:

@misc{mossimage2026,
  title        = {MOSS-Image},
  author       = {{OpenMOSS Team}},
  year         = {2026},
  howpublished = {\url{https://github.com/OpenMOSS/MOSS-Image}}
}
@misc{mossimage2026report,
  title         = {MOSS-Image Technical Report},
  author        = {{MOSI.AI}},
  year          = {2026},
  eprint        = {2610.23374},
  archivePrefix = {arXiv},
  url           = {https://arxiv.org/abs/2610.23374}
}

What it uses

The models are downloaded from Hugging Face, a site that hosts open AI models, and only when you ask. MOSS-Image's model is published there as MOSS-Image-SFT; its text encoder and image decoder come from Qwen and FLUX.2 and are included in that download.

Python libraries, installed alongside:

Local by design

Blokjutsu uses the internet only to download the models, once, and only after a confirmation dialog; it does not go online to generate, edit, or store images, or to check for updates. Everything it writes is kept in ~/Library/Application Support/Blokjutsu.noindex, out of Time Machine backups and Spotlight, and PNGs hold only the image unless the user turns on Settings in PNG. The User's Guide's Running locally lists every file and what Delete all history does with it.

Roadmap

What comes next is in ROADMAP.md.

Bug reports and feature requests

Please report bugs and request features as GitHub issues. For help using Blokjutsu, see the User's Guide and its Frequently asked questions page.

Etymology

Blokjutsu (BLOK-joot-soo, /ˈblɒk.dʒuː.tsuː/), noun. The art of the block.

From Danish blok, "block," and Japanese jutsu (術, じゅつ), "art" or "technique." The name comes from how MOSS-Image works: it treats an image as blocks of pixels, each 16 × 16 square one unit for the model, and transforms them step by step from noise into the finished image.

Design inspiration

The block designs in the icon and the app draw on

• the Kohs block design test, introduced by Samuel C. Kohs in 1920: colored cubes, some faces split diagonally, arranged to match a pattern
• Froebel's gifts, the wooden building blocks of Friedrich Fröbel's first kindergartens
• the primary colors and simple geometry of the Bauhaus

Authors

Blokjutsu was written by Bob Carpenter together with Claude, Anthropic's AI model.

License

Copyright 2026 Bob Carpenter. Apache License 2.0; see LICENSE and NOTICE. blokjutsu/moss_image.py is MOSS-Image's pipeline code, copied unchanged, and blokjutsu/moss_forward.py is adapted from it (both Apache-2.0). "MOSS-Image" is the OpenMOSS Team's name and is used here only to say what this app runs.