DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

Official implementation of "TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models"

[ICML 2024 Best Paper] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)

A fast, clean, responsive Hugo theme.

A simple implimentation of Bayesian Flow Networks (BFN)

Official repository of Evolutionary Optimization of Model Merging Recipes

Large World Model -- Modeling Text and Video with Millions Context

OCR, layout analysis, reading order, table recognition in 90+ languages

StarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and te…

Official code for "Style Aligned Image Generation via Shared Attention"

[ECCV 2024] Official Repository for DiffiT: Diffusion Vision Transformers for Image Generation

Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

A comprehensive deep dive into the world of tokens

Officail Implementation for "Cross-Image Attention for Zero-Shot Appearance Transfer"

PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

⚡ InstaFlow! One-Step Stable Diffusion with Rectified Flow (ICLR 2024)

The official PyTorch implementation for NCSNv2 (NeurIPS 2020)

This repository contains the official implementation of the research paper, "FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization" ICCV 2023

Checkpointable dataset utilities for foundation model training

Implementation of HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models

Text2Cinemagraph: Text-Guided Synthesis of Eulerian Cinemagraphs [SIGGRAPH ASIA 2023]

Tiny AutoEncoder for Stable Diffusion (and other image models)

Generative Models by Stability AI

Code for Fast Training of Diffusion Models with Masked Transformers

The official code of paper "OMS-DPM: Optimizing Model Schedule for Diffusion Probabilistic Model" accepted by ICML 2023

Official implementation of "Controlling Text-to-Image Diffusion by Orthogonal Finetuning".