<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/a256c012c1a3434b9cba63949d979dcc&quot; frameborder=&quot;0&quot; width=&quot;1662&quot; height=&quot;1246&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1246</height><width>1662</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1246</thumbnail_height><thumbnail_width>1662</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/a256c012c1a3434b9cba63949d979dcc-665d3d5b4833fbaa.gif</thumbnail_url><duration>300.929</duration><title>Edit Anything - Nano Banana Hackathon Project</title><description>In this video, I introduce our project called &quot;Edit Anything,&quot; which allows users to easily edit text in images as if they were text boxes. We utilize a technique called image decomposition to extract text from graphics, enabling seamless modifications. I demonstrate the process by editing a graphic with complex text and colors, highlighting our current model&apos;s 74% accuracy across 12 fonts. I encourage viewers to explore this new capability and stay tuned for improvements as we expand our font options. Your feedback and thoughts on this tool would be greatly appreciated!</description></oembed>