gyhandy

AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

llama

Inference code for LLaMA models

TaskMatrix

stanford_alpaca

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

generative-models

Generative Models by Stability AI

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

LLaVA

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

codellama

Inference code for CodeLlama models

LAVIS

LAVIS - A One-stop Library for Language-Vision Intelligence

trl

Train transformer language models with reinforcement learning.

mistral-src

Reference implementation of Mistral AI 7B v0.1 model.

imaginaire

NVIDIA's Deep Imagination Team's PyTorch Library

dreamgaussian

[ICLR 2024 Oral] Generative Gaussian Splatting for Efficient 3D Content Creation

ZoeDepth

Metric depth estimation from a single image

BundleSDF

[CVPR 2023] BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects

OnePose

Code for "OnePose: One-Shot Object Pose Estimation without CAD Models", CVPR 2022

MVDream

Multi-view Diffusion for 3D Generation

WonderJourney

ChatCaptioner

Official Repository of ChatCaptioner

Mini-DALLE3

Mini-DALLE3: Interactive Text to Image by Prompting Large Language Models

Subject-Diffusion

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

Cap3D

[NeurIPS 2023] Scalable 3D Captioning with Pretrained Models

tifa

TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering

DreamDistribution

3D-Copy-Paste

[NeurIPS 2023] 3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection

caption-by-committee

Using LLMs and pre-trained caption models for super-human performance on image captioning.

ablator

Model Ablation Tool-Kit for Deep Learning Model

USCthesis

a LaTeX style for theses and dissertations at USC

Text2Image-for-Detection

DALL-E for Detection: Language-driven Compositional Image Synthesis for Object Detection

ISL