nywang16

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

TaskMatrix

stanford_alpaca

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

alpaca-lora

Instruct-tune LLaMA on consumer hardware

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

dalle-mini

DALL·E Mini - Generate images from a text prompt

metaseq

Repo for external large-scale work

instruct-pix2pix

lit-llama

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

open_flamingo

An open-source framework for training large multimodal models.

Otter

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

textual_inversion

Kandinsky-2

Kandinsky 2 — multilingual text2image latent diffusion model

Emu

Emu Series: Generative Multimodal Models from BAAI

composer

Official implementation of "Composer: Creative and Controllable Image Synthesis with Composable Conditions"

dreambooth

phenaki-pytorch

Implementation of Phenaki Video, which uses Mask GIT to produce text guided videos of up to 2 minutes in length, in Pytorch

bubogpt

BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs

X-VLM

X-VLM: Multi-Grained Vision Language Pre-Training (ICML 2022)

gill

🐟 Code and models for the NeurIPS 2023 paper "Generating Images with Multimodal Language Models".

CM3Leon

An open source implementation of "Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning", an all-new multi modal AI that uses just a decoder to generate both text and images

GRiT

GRiT: A Generative Region-to-text Transformer for Object Understanding (https://arxiv.org/abs/2212.00280)

Subject-Diffusion

Subject-Diffusion:Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuning

MagicBrush

[NeurIPS'23] "MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing".

instruction-tuned-sd

Code for instruction-tuning Stable Diffusion.

T2I-CompBench

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

distribution_augmentation

Code for the paper, "Distribution Augmentation for Generative Modeling", ICML 2020.

HIVE

punctuator

A small seq2seq punctuator tool based on DistilBERT

pytorch_tvc

A PyTorch implementation of TVC