Images

This post is just to show a nice photo of the snake-arranged coals in my BBQ, ready to fire.

Cross-modal embeddings represent a breakthrough in artificial intelligence, enabling understanding and reasoning across different data types within a unified representation space.

FLUX.1-dev is a powerful text-to-image model that produces stunning results, but its 24GB+ memory requirement makes it challenging to run on many systems. GGUF quantization of FLUX.1-dev offers a solution, reducing memory usage by approximately 50% while maintaining excellent image quality.

Black Forest Labs has released FLUX.1-Kontext-dev, an advanced image-to-image AI model that augments existing images using text instructions.

Opengraph image metadata is the meta property og:image. Basically, we want correctly generated tag <meta property="og:image" content="https://....jpg"> for each page in our hugo-based website.

For quite a time I’ve been bugged with this annoyance to put thumbnail images of the pages into static directory. Thats for Mainroad, Rodster and similar Hugo themes.

Sometimes there is a real need to save image from pdf without screenshoting or rendering the pdf on the screen. pdfimages helps with that.

Or another day you want to extract image and text from the pdf…

I usually set video recording settings on Auto. That’s good enough for me. But! If needed - here are the best video recording settings.

Paper-based planning, journalling and note-taking might help with getting the things done in particular and make everything more fullfilling.

My recent fight of this kind was around my old trusty printer/scaner Canon Pixma MP-495.

A dumbphone, also known as a feature phone, is a basic mobile device that offers minimal functionality compared to modern smartphones.

A Digital Detox is a deliberate reduction of using smartphones, televisions, and computers. The primary goal is to mitigate screen overuse and promote offline activities, helping individuals create a more balanced relationship with technology.

Recently Black Forest Labs published a set of text-to-image AI models. These models are told have much higher output quality. Let’s try them out

When I trained object detector AI some time ago - LabelImg was a very helpful tool, but the export from Label Studio to COCO format wasn’t accepted by MMDetection framework..

Cropping, resizing and making borders to the images for this blog pushed me to add this frequently used feature to Linux Mint Cinnamon’s context menu.