Fundamentals of Digital Media Technology(04713901) | Peking University ECE Course Materials

[CVPR 2024] Data and benchmark code for the EgoExoLearn dataset

Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Open-MAGVIT2: Democratizing Autoregressive Visual Generation

Next-Token Prediction is All You Need

[CVPR'2024 Highlight] Official PyTorch implementation of the paper "VTimeLLM: Empower LLM to Grasp Video Moments".

AIStore: scalable storage for AI applications

YaRN: Efficient Context Window Extension of Large Language Models

Official Code for Stable Cascade

A Python-level JIT compiler designed to make unmodified PyTorch programs faster.

VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models (CVPR 2024)

This repository is a curated collection of the most exciting and influential CVPR 2024 papers. 🔥 [Paper + Code + Demo]

[ECCV 2024] PowerPaint, a versatile image inpainting model that supports text-guided object inpainting, object removal, image outpainting and shape-guided object inpainting with only a single model…

LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models

Consistency Distilled Diff VAE

Efficient Triton Kernels for LLM Training

Generative Models by Stability AI

Iterable datapipelines for pytorch training.

A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

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

📺 An End-to-End Solution for High-Resolution and Long Video Generation Based on Transformer Diffusion

[Neurips 2023] T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation

Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI

A very minimal example to get LLM models working with FSDP. The goal is to be minimal, yet scalable to demonstrate the strengths of FSDP.

Ongoing research training transformer language models at scale, including: BERT & GPT-2

Repository for Show-o, One Single Transformer to Unify Multimodal Understanding and Generation.

Enable macOS HiDPI and have a native setting.

A large-scale text-to-image prompt gallery dataset based on Stable Diffusion

MineRL Competition for Sample Efficient Reinforcement Learning - Python Package

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