Wang-Xiaodong1899

DragGAN

Official Code for DragGAN (SIGGRAPH 2023)

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

generative-models

Generative Models by Stability AI

dalle-mini

DALL·E Mini - Generate images from a text prompt

codellama

Inference code for CodeLlama models

tiktoken

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

al-folio

A beautiful, simple, clean, and responsive Jekyll theme for academics

cupy

NumPy & SciPy for GPU

llama-recipes

Scripts for fine-tuning Llama2 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization & question answering. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment.Demo apps to showcase Llama2 for WhatsApp & Messenger

Qwen-VL

The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

img2dataset

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

Ask-Anything

[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.

Video-LLaMA

[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

llm-awq

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

gigagan-pytorch

Implementation of GigaGAN, new SOTA GAN out of Adobe. Culmination of nearly a decade of research into GANs

Llama-X

Open Academic Research on Improving LLaMA to SOTA LLM

Emu

Emu Series: Generative Multimodal Models from BAAI

robotics_transformer

magvit

Official JAX implementation of MAGVIT: Masked Generative Video Transformer

mmc4

MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.

SEED

Official implementation of SEED-LLaMA (ICLR 2024).

ReVersion

ReVersion: Diffusion-Based Relation Inversion from Images

GigaGAN

robotic-transformer-pytorch

Implementation of RT1 (Robotic Transformer) in Pytorch

Instruct2Act

Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model

Visual-LLaMA

Open LLaMA Eyes to See the World

SceneScape

Official Pytorch Implementation for "SceneScape: Text-Driven Consistent Scene Generation"

NUWA-LIP

NÜWA-LIP: Language Guided Image Inpainting with Defect-free VQGAN

ORES

ORES: Open-vocabulary Responsible Visual Synthesis

SSHT-plus-plus

SSHT++