Diffusion Models Python Packages

openvino

OpenVINO™ is an open source toolkit for optimizing and deploying AI inference

openvino-dev

OpenVINO™ is an open source toolkit for optimizing and deploying AI inference

st-attn

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

vsa

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

transformerlab

The open source research environment for AI researchers to seamlessly train, evaluate, and scale models from local hardware to GPU clusters.

deepcache

[CVPR 2024] DeepCache: Accelerating Diffusion Models for Free

image-reward

[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation

cd-fvd

[CVPR 2024] On the Content Bias in Fréchet Video Distance

remove-ai-watermarks

AI watermark remover. CLI and Python library to strip visible and invisible AI watermarks (Gemini / Nano Banana sparkle, SynthID) and provenance metadata (C2PA, EXIF, IPTC) from images.

fastvideo-kernel

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

adafactor8bit

8-bit Adafactor Optimizer with Fused CUDA Kernels

simpletuner

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

deepinv

DeepInverse: a PyTorch library for solving imaging inverse problems using deep learning

transformerlab-cli

The open source research environment for AI researchers to seamlessly train, evaluate, and scale models from local hardware to GPU clusters.

aquiles-image

A high-performance, memory-efficient inference server for diffusion models, compatible with the OpenAI client

rose-opt

🌹 Rose: Range-Of-Slice Equilibration PyTorch optimizer. Stateless optimization through range-normalized gradient updates.

onediff

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

onediffx

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

civitai-hub

huggingface_hub, but for CivitAI — inspect and download models/LoRAs from the CLI or as a Python library

monai-generative

MONAI Generative Models makes it easy to train, evaluate, and deploy generative models and related applications

fastvideo

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

openvino-nightly

OpenVINO™ is an open source toolkit for optimizing and deploying AI inference

azula

Diffusion models in PyTorch

diffusion-model-framework

A simple framework for training diffusion models.