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.

SD.Next: All-in-one WebUI for AI generative image and video creation, captioning and processing

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

Stable diffusion for real-time music generation

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

🔥 [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity

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

Fast stable diffusion on CPU and AI PC

Code repository for Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model.

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

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

A SOTA quantization toolkit for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers|简洁且高效的量化工具包

Scalable and memory-optimized training of diffusion models

https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.

Inpaint Anything extension performs stable diffusion inpainting on a browser UI using masks from Segment Anything.

Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.

a self-hosted webui for 30+ generative ai

App showcasing multiple real-time diffusion models pipelines with Diffusers

Transfer the ControlNet with any basemodel in diffusers🔥

The most easy-to-understand tutorial for using LoRA (Low-Rank Adaptation) within diffusers framework for AI Generation Researchers🔥