Development client for Mellon

Speak Friend and Enter

Converts pixel-art-style images such as those from generative models or low-quality sprites to true resolution usable assets

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

DiffusersServer es un servidor de inferencia basado en FastAPI y uvicorn que permite generar imágenes a partir de texto (Text-to-Image) utilizando modelos de difusión.

A reimplementation of Stable Diffusion 3.5 in pure PyTorch

Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers" (ICML 2025)

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

dgenerate is a scriptable command line tool (and library) for generating images and animation sequences using stable diffusion and related techniques, with an accompanying GUI scripting environment.

Scalable and memory-optimized training of diffusion models

[ICCV 2025] VisualCloze: A universal image generation framework that can support a wide range of in-domain tasks and generalize to unseen ones. (🔥 🔥 🔥 Merged into offical pipelines of diffusers.)

Towards Human-Sounding Speech

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

An out-of-the-box inference acceleration engine for Diffusion and DiT models

Agent S: an open agentic framework that uses computers like a human

[CVPR 2025] This is an official inference code of the paper "BizGen: Advancing Article-level Visual Text Rendering for Infographics Generation" . Project page: https://bizgen-msra.github.io/

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

A high-throughput and memory-efficient inference and serving engine for LLMs

SoftFill is a Diffusers pipeline based on Differential Diffusion, incorporating input and preprocessing modifications that enable it to function more like "soft inpainting"—without requiring additi…

[ICCV 2025] STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution

This repo implements a Stable Diffusion model in PyTorch with all the essential components.

[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

This repository contains demos I made with the Transformers library by HuggingFace.

An extremely fast Python package and project manager, written in Rust.

Official repository for LTX-Video

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"