<?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/b4a648e9dedb4502b0bf872c371545c4&quot; frameborder=&quot;0&quot; width=&quot;1920&quot; height=&quot;1440&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1440</height><width>1920</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1440</thumbnail_height><thumbnail_width>1920</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/b4a648e9dedb4502b0bf872c371545c4-fe68de074f4f3d73.gif</thumbnail_url><duration>1781.078</duration><title>Generating AI Music Video Ads, Stefan</title><description>This Loom demonstrates using the newest Stefan Brain SB 1.5 version to generate direct-response music video and song ad concepts, then quickly tests several outputs for FraserSkin. The creator notes that active subscribers and active paying or trial users get access, with the update rolling out to the main platform in one to two weeks, and says the concept generation took about 2 to 3 minutes. They select concepts like Sandpaper Funk, Ballad of Dubbo Dust, Hard Yakka Dirty Bakka, and The Backstings Back, generating multiple variations with different styles and sometimes seeing issues like inconsistent singers. By around 7:07 am, several videos are ready for review, with one Disney-style concept judged a dud and others shared as strong results.</description></oembed>