Apple MLX native implementations of state-of-the-art generative image & video models
MFLUX is a native MLX implementation of generative image models that runs locally on Mac computers. It is for generating images with supported models through command-line tools or a Python API. The catalogue skills and instruction support workflows built around these image-generation models.
Skill Claude CodeCodex
Remediates GitHub Dependabot alerts for mflux in one dependency-security change. Use when auditing, clamping, or upgrading Python dependencies in pyproject.toml and uv.lock, or when validating whether a branch will close Dependabot findings before opening a PR.
Skill Claude CodeCodexCursor
Navigate MFLUX CLI capabilities, locate commands by area, and summarize supported features.
Skill Claude CodeCodexCursor
Debug MLX ports by comparing against a PyTorch/diffusers reference via exported tensors/images (export-then-compare).
Skill Claude CodeCodexCursor
Set up and work in the mflux dev environment (arm64 expectation, uv, justfile recipes, lint/format/test).
Skill Claude CodeCodexCursor
Manually validate mflux CLIs by exercising the changed paths and reviewing output images/artifacts.
Skill Claude CodeCodexCursor
Port ML models into mflux/MLX with correctness-first validation, then refactor toward mflux style.
Skill Claude CodeCodexCursor
Write a hermetic "tiny" model-saving test for an mflux model — a fast twin of the slow save/load test that runs the real ModelSaver/WeightLoader/WeightApplier seam on real component classes at toy dimensions, with no downloads or image generation. Use when asked to "make tiny test for ".
Skill Claude CodeCodexCursor
Make a clean PR in mflux (inspect diff, quick verification, commit, push, open PR) using repo conventions.
Skill Claude CodeCodexCursor
Prepare a release in mflux (version bump + uv lock; release notes are harvested from PR release-note blocks and live in GitHub Releases). Use when preparing a release branch or release PR.
Skill Claude CodeCodexCursor
Run tests in mflux (fast/slow/full), preserve image outputs, and handle golden image diffs safely.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: