iamlockelightning

flash-attention

Fast and memory-efficient exact attention

MMLongBench-Doc

Official Repository of MMLONGBENCH-DOC: Benchmarking Long-context Document Understanding with Visualizations

Stack-Solver

Stack Solver is an app for the optimisation of palletizing and shipping items.

picx

🏞️ PicX 是一款基于 GitHub API 开发的图床工具，提供图片上传托管、生成图片链接和常用图片工具箱服务。

aseprite

Animated sprite editor & pixel art tool (Windows, macOS, Linux)

MaskDiT

Code for Fast Training of Diffusion Models with Masked Transformers

ShiArthur03

LivePortrait

Bring portraits to life!

VCR

Official Repo for the paper: VCR: Visual Caption Restoration. Check arxiv.org/pdf/2406.06462 for details.

anole

Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation

cambrian

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

ml-4m

4M: Massively Multimodal Masked Modeling

mage

A PyTorch implementation of MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis

ImprovedNAT

A PyTorch implementation of the paper "Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis"

MaskedVectorQuantization

Official Pytorch Implementation of Our CVPR2023 Paper: "Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation"

Open-MAGVIT2

Open-MAGVIT2: Democratizing Autoregressive Visual Generation

audioseal

Localized watermarking for AI-generated speech audios, with SOTA on robustness and very fast detector

chameleon

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

audiocraft

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

MINT-1T

MINT-1T: A one trillion token multimodal interleaved dataset.

vector-quantize-pytorch

Vector (and Scalar) Quantization, in Pytorch

rq-vae-transformer

The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22)

KataCR

A non-embedded AI for Clash Royale based on RL and CV.

ClashRoyaleBuildABot

A platform for creating bots to play Clash Royale

OmniTokenizer

OmniTokenizer: one model and one weight for image-video joint tokenization.

Libra

Simple PyTorch implementation of "Libra: Building Decoupled Vision System on Large Language Models" (accepted by ICML 2024)

LlamaGen

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

ChatTTS

A generative speech model for daily dialogue.

Bend

A massively parallel, high-level programming language

SEED

Official implementation of SEED-LLaMA (ICLR 2024).