VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation

Allegro is a powerful text-to-video model that generates high-quality videos up to 6 seconds at 15 FPS and 720p resolution from simple text input.

Next-Token Prediction is All You Need

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

The Repo is for processing the Large Video Dataset WebVid-10M, include sample, track, and so on

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

MM-Instruct: Generated Visual Instructions for Large Multimodal Model Alignment

This is an implemention of llm attack on chatglm2

Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

The conventional commits specification

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

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

[NeurIPS 2024 Oral][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-sim…

Ongoing research training transformer models at scale

Open-Sora: Democratizing Efficient Video Production for All

Grok open release

DALL·E Mini - Generate images from a text prompt

Modeling, training, eval, and inference code for OLMo

Emu Series: Generative Multimodal Models from BAAI

Official Code for Stable Cascade

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