mflux-community/mflux

Health v2 · maintenance only

Adoption not part of the score

2291 stars · 172 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

MFLUX is a native MLX implementation of state-of-the-art generative image and video models (Flux, Qwen-Image, Z-Image, and others), ported line-by-line from Hugging Face Diffusers/Transformers. It runs locally on Apple Silicon Macs via a CLI and Python API.

Use cases

• generate images locally on a mac
• run flux text-to-image on apple silicon
• convert huggingface diffusers models to mlx
• generate images from a text prompt via cli
• run generative image models without a gpu server
• quantize image models for faster local inference

When to choose

• you have an Apple Silicon Mac and want fast local image generation
• you want readable, minimal MLX implementations of diffusion models
• you prefer a simple CLI or small Python API over heavyweight frameworks

When to avoid

• you need CUDA/NVIDIA GPU support
• you need the full flexibility of Hugging Face Diffusers
• you need production serving of image models at scale

Facets

library · maturity active

machine-learning image-processing cli llm-inference artificial-intelligence image-processing machine-learning gpu-computing python cli mlx apple-silicon diffusion-models text-to-image flux generative-ai local-inference macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="mflux-community/mflux")