<?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/21374169e08f45fe9c358f8ed7971a14&quot; frameborder=&quot;0&quot; width=&quot;1794&quot; height=&quot;1345&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1345</height><width>1794</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1345</thumbnail_height><thumbnail_width>1794</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/21374169e08f45fe9c358f8ed7971a14-d0352608ea88bf63.gif</thumbnail_url><duration>973.885</duration><title>Improving Character Canvases for AutoAI</title><description>In this video, I discuss the importance of character canvases and how to ensure consistency in AutoAI outputs. I walk through the necessary column names and details required for effective character prompts, emphasizing the need for specificity in attributes like age and physical features. I also highlight common mistakes and how to correct them to achieve better results. Please make sure to implement these changes in your character canvases for improved outputs.</description></oembed>