The Kandinsky 5.0 Video Lite Text to Video workflow is a streamlined process for generating high-quality videos from text prompts in both English and Russian. This workflow leverages the Kandinsky model, known for its efficiency and visual fidelity, to transform simple text inputs into dynamic video content. The workflow is designed to handle resolutions of 768x512, producing videos that can be either 5 or 10 seconds long, depending on the configuration. The nodes used in this workflow, including SaveVideo and MarkdownNote, facilitate the seamless conversion of text to video, ensuring that users can easily save and annotate their creations. The model's lightweight nature, at just 2 billion parameters, makes it accessible for users with varying computational resources, without compromising on the quality of the output.