To track the latest paper for embedding (including text/text-code/text-image embeddings)

Adversarial learning system which generate image from text description using self-attention modules

微信小程序的图文编辑功能，可针对单个输入框的文字进行简单样式调整，在文字中间插入、删除图片；

11000-Image-Video-caption-data-of-human-action

Replication Code for: Making Text-Image Connection Formal and Practical

lmmtoolkit is a toolkit for Multi-Modal Learning

A PyTorch implementation of "TextFuseNet: Scene Text Detection with Richer Fused Features".

To Fuse Semantic and Positional Clues with Cross-Attention for Scene Text Recognition

Paging menu controller having text and imageview in the Tab

A small script for CLIP attn entropy plots

Multi-Modal Image Generation for News Stories

This project represents a graphic design technique that uses printable characters from the ASCII standard to create images and animations.

Text-Image-Text is a bidirectional system that enables seamless retrieval of images based on text descriptions, and vice versa. It leverages state-of-the-art language and vision models to bridge the gap between textual and visual representations.

20011--Image-Caption-Data-Of-OCR-In-Natural-Scenes

A Light Neural Network To Control Stable Diffusion Spatial Information tuned by Chinese

This repository is based on the work done for the Bangla Handwritten Line Segmentation

convert raster images to ASCII art

一个基于内容的图像检索系统

[BMVC 2023] Zero-shot Composed Text-Image Retrieval

Software tool that compresses text binary images (lossless compression) to less than 0.002% of their original size on average.