If you seek something simple, non-commandline, easy to use and with a GUI, then Capture2Text is the best I know so far. Source: over 2 years ago

Capture2Text is FOSS. It uses Tesseract as it's OCR engine, which is great as you can use different language data files to find the one that is the most accurate for your purposes. Source: over 2 years ago

Capture2Text is the simplest solution and it works surprisingly well with the Cold Steel/Hajimari text boxes... Once it runs in the background press a previously assigned hotkey and select the area on the screen to be captured. I recommend deactivating its popup window, you just want the text to be copied into the clipboard. Source: almost 3 years ago

You should have a look at Capture2Text and ShareX. They offer OCR translation (ShareX links to google translator in your browser, when you do OCR Translation, I think). Source: over 3 years ago

The core of EchoAI involves two Google Sheets (or CSV files) that feed data into a Stable Diffusion API (Auto1111) or any online Stable Diffusion service with API support, like leonardo.ai. Here’s a glimpse of what the Sheet looks like: [ Google Sheet ]. The Python script combines elements from each column of the sheet (environment, ambiance, etc.) to generate unique scenes using the model of your choice, or even... Source: 6 months ago

I'm wondering if there is something similar to leonardo.ai live canvas for locally run setups. Assuming it would have to use sdturbo or the like. Hoping a 4090 could run something like that! Lol. Source: 6 months ago

I'm wondering the best way to make videos frame-by-frame that flow into each other using leonardo.ai. Source: 9 months ago