Beast code in Giters

sirius541's starred repositories

TextRecognitionDataGenerator

A synthetic data generator for text recognition

Language:PythonMIT321200

florence2-finetuning

Quick exploration into fine tuning florence 2

Language:Jupyter NotebookMIT24400

baby-llama2-chinese

用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.

Language:PythonMIT242600

MINI_LLM

This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.

Language:Python32400

DocRes

[CVPR 2024] DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks

Language:PythonMIT27100

Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet, NasNet, Residual Attention Network, SENet, WideResNet)

Language:Python417100

Transformer

Transformer seq2seq model, program that can build a language translator from parallel corpus

Language:PythonApache-2.0133200

LightGlue

LightGlue: Local Feature Matching at Light Speed (ICCV 2023)

Language:PythonApache-2.0327100

lscm

Least squares conformal mapping implemented in C++

Language:C++MIT10700

PoissonRecon

Poisson Surface Reconstruction

Language:C++MIT153700

DocTrPP

DocTr++ in PaddlePaddle

Language:Python3600

doc3D-dataset

A hybrid dataset for document unwarping (Paper: https://www3.cs.stonybrook.edu/~cvl/projects/dewarpnet/storage/paper.pdf)

Language:ShellMIT15900

doc3D-renderer

Blender rendering codes for doc3D-dataset (Paper: https://www3.cs.stonybrook.edu/~cvl/projects/dewarpnet/storage/paper.pdf)

Language:Python11000

sd-face-editor

Face Editor for Stable Diffusion

Language:PythonMIT101400

YOLO-World

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

Language:PythonGPL-3.0425200

InstantID

InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

Language:PythonApache-2.01079500

Grounded-Segment-Anything

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

Language:Jupyter NotebookApache-2.01466000

Document-Dewarping-with-Control-Points

Document Dewarping with Control Points

Language:PythonMIT15000

ConvNeXt

Code release for ConvNeXt model

Language:PythonMIT569600

PaperEdge

The code and the DIW dataset for "Learning From Documents in the Wild to Improve Document Unwarping" (SIGGRAPH 2022)

Language:PythonMIT11500

FastChat

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

Language:PythonApache-2.03634400

AnyText

Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>

Language:PythonApache-2.0419100

modelscope

ModelScope: bring the notion of Model-as-a-Service to life.

Language:PythonApache-2.0675500

SadTalker

[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

Language:PythonNOASSERTION1157300

Vary

[ECCV 2024] Official code implementation of Vary: Scaling Up the Vision Vocabulary of Large Vision Language Models.

Language:Python169800

shap-e

Generate 3D objects conditioned on text or images

Language:PythonMIT1154300

StreamDiffusion

StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

Language:PythonApache-2.0943100

KAIR

Image Restoration Toolbox (PyTorch). Training and testing codes for DPIR, USRNet, DnCNN, FFDNet, SRMD, DPSR, BSRGAN, SwinIR

Language:PythonMIT286700

PromptSR

PyTorch code for our paper "Image Super-Resolution with Text Prompt Diffusion"

10100

AnyDoor

Official implementations for paper: Anydoor: zero-shot object-level image customization

Language:PythonMIT390700