Flux Python Packages

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

influxdb-client

InfluxDB 2.0 python client

cobra

COBRApy is a package for constraint-based modeling of metabolic networks.

mflux

Apple MLX native implementations of state-of-the-art generative image & video models

remove-ai-watermarks

Remove visible and invisible AI watermarks and provenance metadata from images and video. Python library and CLI for SynthID, C2PA, EXIF, IPTC, XMP, and common generative-AI marks.

flux-python

Python bindings generator for flux-core

executorlib

Up-scale python functions for high-performance computing (HPC)

inferhost

Self-hosted multi-modal AI server: chat/vision LLMs (Qwen, Llama, Gemma, DeepSeek), text-to-speech (OuteTTS, Qwen3-TTS) and image generation (SDXL, Flux, Z-Image, Qwen-Image) behind one OpenAI-compatible endpoint. Wraps llama.cpp + stable-diffusion.cpp, auto-fetches GGUF models from Hugging Face, VRAM hot-swap, speculative decoding, no compiling.

mlx-gen

Generative image and video runtimes for Apple Silicon (MLX): text/image-to-image, instruction editing, masked edit, text/image/reference-to-video, video editing, and restoration.

aquiles-image

A high-performance, memory-efficient inference server for diffusion models (image/video generation), compatible with the OpenAI client

mlx-teacache

TeaCache step-skipping for FLUX, Qwen-Image & Z-Image diffusion on Apple Silicon, in pure MLX

micom

Python package to study microbial communities using metabolic modeling.

socaity

SDK for generative AI.

stable-diffusion-cpp-python

stable-diffusion.cpp bindings for python

mlx-openai-server

A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Python and powered by the FastAPI framework, it provides an efficient, scalable, and user-friendly solution for running MLX-based vision and language models locally with an OpenAI-compatible interface.

mlx-taef

Tiny AutoEncoders (TAESD family) for diffusion latents on Apple Silicon — pure MLX. Live previews + low-memory decode for FLUX.1, FLUX.2 Klein, SD1.x, SDXL.

pympipool

Up-scale python functions for high-performance computing (HPC)

hicache-pp

Drop-in TaylorSeer/HiCache basis upgrade — training-free diffusion acceleration via a Dynamic Mode Decomposition (Prony) exponential feature-forecast basis. Not the SGLang KV-cache HiCache.

flux-pro-cli

Python CLI for Black Forest Labs Flux AI image generation and editing through Ace Data Cloud.

para-attn

https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching

diskstack

Merge several dumps of one floppy disk into the best possible image, and say what is still missing. Reads .scp, KryoFlux .raw, .hfe and sector images, votes sector by sector, and prints the gw read --tracks= command for what is still bad.

fluxfootprints

Used for calculation of measurement footprint of water vapor and CO2 flux by an eddy covariance station.

mlx-dfloat

Run DFloat11 losslessly compressed BF16 checkpoints on Apple Silicon with MLX and a Metal decode kernel; today that runs FLUX.1 on a 32 GB Mac with weights about 30% smaller

runapi-flux

RunAPI Flux SDK for image generation and editing in JavaScript, Python, Ruby, Go, Java, and PHP