Encode text as reversible unit-distance graph images
GLEE: Geometric Laplacian Eigenmap Embedding
Graph embedding seeks to build a low-dimensional representation of a graph G. This low-dimensional representation is then used for various downstream tasks. One popular approach is Laplacian Eigenmaps (LE), which constructs a graph embedding based on the spectral properties of the Laplacian matrix of G. The intuition behind it, and many other embedding techniques, is that the embedding of a graph must respect node similarity: similar nodes must have embeddings that are close to one another. Here, we dispose of this distance-minimization assumption. Instead, we use the Laplacian matrix to find an embedding with geometric properties instead of spectral ones, by leveraging the so-called simplex geometry of G. We introduce a new approach, Geometric Laplacian Eigenmap Embedding, and demonstrate that it outperforms various other techniques (including LE) in the tasks of graph reconstruction and link prediction.
Text rendering and effects using GPU-computed distances
Text rendering is cursed. Anyone who has worked on text will tell you the same; whether it's about layout, bi-directional, shaping, Unicode, or the rendering itself, it's never a completely solved problem. In my personal case, I've been working on trying to render text in the context of a compositing engine for creative content. I needed crazy text effects, and I needed them to be reasonably fast, which implied working with the GPU as much as possible. The distance field was an obvious requirement because it unlocks anti-aliasing and the ability to make many great effects for basically free.
ASCII characters are not pixels: a deep dive into ASCII rendering
A look at how I used shape vectors to achieve sharp, high-quality ASCII rendering.
Generating 3D Meshes From Text
I recently had a desire to convert text to 3D meshes that I could render and manipulate as part of my Geotoy project and Geoscript language. I did some research into tools and libraries that could solve different pieces of this, and I put together a pipeline that implements the whole thing - yielding nice, 2-manifold 3D meshes with arbitrary fonts, text styles, and more.
Introducing ChatGPT Images 2.0
ChatGPT Images 2.0 introduces a state-of-the-art image generation model with improved text rendering, multilingual support, and advanced visual reasoning.
Free WordArt Generator - Create 90s Text Effects Online | Make WordArt
Free Online WordArt Generator - Create Nostalgic 90s Text Effects Instantly. No Photoshop needed! Download as PNG or use in iMessage, Google Docs. The original MS Office retro styles.
SOTA OCR with Core ML and dots.ocr
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
The Future of Text
We are a community dedicated to working on how we can better develop text to augment our capabilities and we invite you to join us. We believe that the potential of richly interactive text to truly augment how we think & communicate is massive. Text after all, is externalized symbols we can interact with to extend our mind’s reach. Therefore text is not just a medium, it is also a tool for thought, and we are looking Beyond Visual Range.
Rotary Positional Embeddings: A Detailed Look and Comprehensive Understanding
Since the “Attention Is All You Need” paper in 2017, the Transformer architecture has been a cornerstone in the realm of Natural Language…
MD Thermochrome by Mass-Driver - Future Fonts
Our written world is made from little dots: little dots of ink from a printer; phosphors or pixels on a screen; blackened thermal paper on a sales receipt. MD Thermochrome is a typeface designed around little dots. It’s not a faithful mimicry of any single printing technique, but an allusion to several — the coarse grid of dot-matrix printers, the visible scanlines of CRT terminal fonts, the varying dot size of over- and under-inked documents from any number of technologies. Built on a consistent (but not quite square) grid, Thermochrome features five discrete italic angles (Upright, Italic, Inclined, Retalic, Reclined), eight weights, and over 100 icons and symbols.
Wiretext — Unicode Wireframe Design Tool
A spatial design tool where everything renders as Unicode box-drawing characters. Share as text.
ascorbic/og-edge
Generate Open Graph images with Deno and Netlify Edge Functions, no framework needed.
Unsloth AI on Twitter / X
DeepSeek releases DeepSeek-OCR 2. 🐋The new 3B model achieves SOTA visual, document and OCR understanding.DeepEncoder V2 is introduced which enables the model scan images in same logical order as humans, boosting OCR accuracy.Instead of traditional vision LLMs which read an… pic.twitter.com/9WYaSGD7XU— Unsloth AI (@UnslothAI) January 27, 2026
How I Write Alt-Text - 12 Aug 2026 03:30 UTC
‘Alt-text’ is short for alternative text, and is used to convey the substance of visual content as text. It is important for people with visual disabilities, though is beneficial for a wide range of people. It is useful for low-speed connections where an image might not load, for searching for an image, for SEO/AIO/GEO, for cases where a link to an image is broken, for understanding context, and for a variety of other gains.
ChatGPT Images 2.0 is a breakthrough that could fundamentally reshape graphic generation
OpenAI is adding reasoning and web search to its ChatGPT Images 2.0 image generator. The model can now create up to eight consistent images from a single prompt and handles text in general, and especially in non-Latin scripts, significantly better.
