The tool extracts texts, images, or videos argon with the design styles like font, colour and layout from the HTML sources. While organising the virtual assets into sequences of shots, the tool maintains a look and feel similar to the source page.
URL2Video uses all these elements to render materials into a video. Google created a team of designers that are familiar with web designs and video creation to understand various aspects of webpage derived from heuristics.
The tool uses this information to analyse the content and select video or picture while preserving the design styles. Based on the user preference, the tool selects other elements and ranks key elements to create a video.
The official blog post reads, “We envision a future where creators focus on making high-level decisions and an ML model interactively suggests detailed temporal and graphical edits for a final video creation on multiple platforms.”
Google is trying to position this tool as an automatic approach to convert web page into a short video, considering temporal and visual constraints. The tool also picks key details such as fonts, colours, text, layouts from the website and highlights it in the rendered output.