The Python programming language

DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model.

Writing FLUX in Triton

Official inference repo for FLUX.1 models

Bytie the Discord Bot but in Rust

High-throughput serving engine for AI models. Flexible. Friendly interface. Enterprise scale.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

AuraSR: GAN-based Super-Resolution for real-world

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

Generative models for conditional audio generation

Object-oriented handling of audio data, with GPU-powered augmentations, and more.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Minimal implementation of scalable rectified flow transformers, based on SD3's approach

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Karras et al. (2022) diffusion models for PyTorch

[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly …

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

A nearly-live implementation of OpenAI's Whisper.

A single API for text-to-image, built on fal that supports all Stable Diffusion variants

This project aim to reproduce Sora (Open AI T2V model), but we only have limited resource. We deeply wish the all open source community can contribute to this project.

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

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

wheels for torchmcubes

A demo application using fal.realtime and the lightning fast SDXL API provided by fal

SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.