Diffusers Python Packages

auto-round

A simple and effective post training quantization toolkit for high-accuracy low-bit LLM inference|简洁且高效的后训练量化工具包

vsa

A unified inference and post-training framework for accelerated video generation.

st-attn

A unified inference and post-training framework for accelerated video generation.

mflux

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

optimum-rbln

⚡ A seamless integration of HuggingFace Transformers & Diffusers with RBLN SDK for efficient inference on RBLN NPUs.

auto-round-nightly

A simple and effective post training quantization toolkit for high-accuracy low-bit LLM inference|简洁且高效的后训练量化工具包

auto-round-lib

A simple and effective post training quantization toolkit for high-accuracy low-bit LLM inference|简洁且高效的后训练量化工具包

xinference

Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.

entail-ai

Checks that what a model's files declare is what the inference engine runs (transformers, vLLM, SGLang, diffusers)

abstractvision

Model-agnostic generative vision for Python and AbstractCore — text/image/video generation via MLX-Gen, Diffusers, stable-diffusion.cpp, and OpenAI-compatible APIs.

diffusers-workflow

MCP server, workflow wrapper and web app for Hugging Face diffusers

onediff

OneDiff: An out-of-the-box acceleration library for diffusion models.

datasetrising

Toolchain for creating custom datasets and training Stable Diffusion (1.x, 2.x, XL) models and LoRAs

abstractmusic

Model-agnostic remote and local text-to-music/audio generation for the AbstractFramework ecosystem. Lightweight base install; optional local runtimes (ACE-Step, Diffusers).

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

fastvideo-kernel

A unified inference and post-training framework for accelerated video generation.

onediffx

OneDiff: An out-of-the-box acceleration library for diffusion models.

simpletuner

A general fine-tuning kit geared toward image/video/audio diffusion models.

nndeploy

一款简单易用和高性能的AI部署框架 | An Easy-to-Use and High-Performance AI Deployment Framework

auto-round-hpu

A simple and effective post training quantization toolkit for high-accuracy low-bit LLM inference|简洁且高效的后训练量化工具包

fastvideo

A unified inference and post-training framework for accelerated video generation.

mship

Self-hosted, OpenAI-compatible inference for the agentic era: reasoning LLMs, universal tool calling, and the Responses API alongside embeddings, speech, and image models — many models sharing your GPUs, one gateway. Powered by Ray Serve.

diffused

🤗 Generate images with diffusion models.