<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Generative AI on Coderrob</title><link>https://coderrob.com/tags/generative-ai/</link><description>Recent content in Generative AI on Coderrob</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Sat, 15 Feb 2025 14:42:11 -0600</lastBuildDate><atom:link href="https://coderrob.com/tags/generative-ai/index.xml" rel="self" type="application/rss+xml"/><item><title>Sora Text to Video: Playing with AI Like It's 2049</title><link>https://coderrob.com/posts/sora-text-to-video-playing-with-ai-like-its-2049/</link><pubDate>Sat, 15 Feb 2025 14:42:11 -0600</pubDate><guid>https://coderrob.com/posts/sora-text-to-video-playing-with-ai-like-its-2049/</guid><description>&lt;p&gt;I finally spent some time experimenting with &lt;a href="https://openai.com/sora/"&gt;Sora&lt;/a&gt;, and the shift from text-to-image to text-to-video feels bigger than I expected.&lt;/p&gt;
&lt;p&gt;I have used Stable Diffusion for a long time. Image generation already changed how I think about prompts, style, references, and iteration.&lt;/p&gt;
&lt;p&gt;Video adds another layer.&lt;/p&gt;
&lt;p&gt;You are not just describing what something looks like anymore.&lt;/p&gt;
&lt;p&gt;You are describing what happens.&lt;/p&gt;
&lt;h2 id="prompting-a-moment"&gt;Prompting a Moment&lt;/h2&gt;
&lt;p&gt;With image generation, a prompt describes a frame.&lt;/p&gt;</description></item><item><title>Stable Diffusion Explained Like I Am 5</title><link>https://coderrob.com/posts/stable-diffusion-explained-like-i-am-five/</link><pubDate>Thu, 10 Nov 2022 15:09:17 -0600</pubDate><guid>https://coderrob.com/posts/stable-diffusion-explained-like-i-am-five/</guid><description>&lt;p&gt;Imagine &amp;ldquo;a world, earth, seen from space, 8k, unreal engine, detailed, photorealistic&amp;rdquo;&amp;hellip;&lt;/p&gt;
&lt;p&gt;&lt;img src="https://coderrob.com/img/what-a-world.png" alt="Positive prompt:&amp;ldquo;a world, earth, seen from space, 8k, unreal engine, detailed, photorealistic&amp;rdquo;"&gt;&lt;/p&gt;
&lt;p&gt;Remember the common phrase, &amp;ldquo;a picture is worth a thousand words&amp;rdquo;? Well, it&amp;rsquo;s time to rethink that.&lt;/p&gt;
&lt;p&gt;With advancements in image generation technology, we may need to start saying, &amp;ldquo;a few words are worth thousands of pictures.&amp;rdquo;&lt;/p&gt;
&lt;p&gt;This technology is simply astonishing.&lt;/p&gt;
&lt;p&gt;Any image. Any concept. Any quality. Any style. Near-instant results.&lt;/p&gt;</description></item></channel></rss>