华南理工大学硕博士学位论文模板(LaTeX)。Latex templates for the thesis of South China University of Technology

This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."

Janus-Series: Unified Multimodal Understanding and Generation Models

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

[CVPR'25] SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding

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

The research collection of typography

Code for generating synthetic text images as described in "Synthetic Data for Text Localisation in Natural Images", Ankush Gupta, Andrea Vedaldi, Andrew Zisserman, CVPR 2016.

CVPR2022 (Oral) - Rethinking Semantic Segmentation: A Prototype View

Official inference repo for FLUX.1 models

Official PyTorch implementation for "Semantically Coherent Montages by Merging and Splitting Diffusion Paths", presenting the Merge-Attend-Diffuse operator (ECCV24)

[ECCV 2024] official code for "Long-CLIP: Unlocking the Long-Text Capability of CLIP"

微软 tts 文本转语音 音频下载

Oracle Bone Script data collected by VLRLab of HUST

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

Official PyTorch Implementation of "DiffusionPen: Towards Controlling the Style of Handwritten Text Generation" - ECCV 2024

Font files available from Google Fonts, and a public issue tracker for all things Google Fonts

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。

Official implementation of FIFO-Diffusion: Generating Infinite Videos from Text without Training (NeurIPS 2024)

UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models

Official code for the paper: Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

Official Code for ECCV 2024 paper — One-Shot Diffusion Mimicker for Handwritten Text Generation