bjtuln

MGM

Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

ComfyUI

The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

clip-interrogator

Image to prompt with BLIP and CLIP

LAVIS

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

InternLM-XComposer

InternLM-XComposer2 is a groundbreaking vision-language large model (VLLM) excelling in free-form text-image composition and comprehension.

sd-scripts

CV_papers_arxiv_daily

Daily feed of this day's research articles about Computer Vision published to https://arxiv.org.

segmoe

HI-Diff

PyTorch code for our NeurIPS 2023 paper "Hierarchical Integration Diffusion Model for Realistic Image Deblurring"

MyArxiv

Arxiv个性化定制化模版，实现对特定领域的相关内容、作者与学术会议的有效跟进。

NeRCo

[ICCV 2023] Implicit Neural Representation for Cooperative Low-light Image Enhancement

parseq

Scene Text Recognition with Permuted Autoregressive Sequence Models (ECCV 2022)

paper-reading

深度学习经典、新论文逐段精读

Restormer

[CVPR 2022--Oral] Restormer: Efficient Transformer for High-Resolution Image Restoration. SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.

stable-diffusion-webui

Stable Diffusion web UI

TaskMatrix

BELLE

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

mmocr

OpenMMLab Text Detection, Recognition and Understanding Toolbox

ImageForensicsOSN

character_set

china_area

2024年**全国5级行政区划（省、市、县、镇、村）

traditional-chinese-text-recogn-dataset

繁體中文OCR文字識別數據集

synthtiger

Official Implementation of SynthTIGER (Synthetic Text Image Generator), ICDAR 2021

TextRecognitionDataGenerator

A synthetic data generator for text recognition

maxim-pytorch

[CVPR 2022 Oral] PyTorch re-implementation for "MAXIM: Multi-Axis MLP for Image Processing", with *training code*. Official Jax repo: https://github.com/google-research/maxim

DocTr

The official code for “DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction”, ACM MM, Oral Paper, 2021.

code-server

VS Code in the browser

FGVC-PIM

Pytorch implementation for "A Novel Plug-in Module for Fine-Grained Visual Classification". fine-grained visual classification task.