<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
	<channel>
		<title>Vision Models on Jamie Ede</title>
		<link>https://jamieede.com/tags/vision-models/</link>
		<description>Recent content in Vision Models on Jamie Ede</description>
		<generator>Hugo</generator>
		<language>en-US</language>
		
		
		
		
			<lastBuildDate>Sat, 11 Jul 2026 00:00:00 +0000</lastBuildDate>
		
			<atom:link href="https://jamieede.com/tags/vision-models/index.xml" rel="self" type="application/rss+xml" />
			<item>
				<title>AI-assisted captions, alt text, and tags with Workers AI vision models</title>
				<link>https://jamieede.com/posts/ai-assisted-captions-alt-text-and-tags/</link>
				<pubDate>Sat, 11 Jul 2026 00:00:00 +0000</pubDate>
				<guid>https://jamieede.com/posts/ai-assisted-captions-alt-text-and-tags/</guid>
				<description>&lt;p&gt;Writing alt text for every photograph is the boring half of running a photography site. A vision model can take the first pass.&lt;/p&gt;&#xA;&lt;p&gt;This is the final post in the &lt;a href=&#34;https://jamieede.com/posts/building-a-photography-portfolio-on-cloudflares-full-stack/&#34; &gt;photography portfolio series&lt;/a&gt;&#xA;. It covers the &lt;a href=&#34;https://developers.cloudflare.com/workers-ai/&#34; target=&#34;_blank&#34; &gt;Workers AI&lt;/a&gt;&#xA; suggestions that power the description, title, alt text, tag, and album-description fields on &lt;a href=&#34;https://alex.edestudio.us&#34; target=&#34;_blank&#34; &gt;alex.edestudio.us&lt;/a&gt;&#xA; and &lt;a href=&#34;https://jamie.edestudio.us&#34; target=&#34;_blank&#34; &gt;jamie.edestudio.us&lt;/a&gt;&#xA;: how the model dispatcher picks an API shape, why the prompts read more like creative-writing briefs than instructions, and where Workers AI is genuinely useful versus where it confidently invents.&lt;/p&gt;</description>
			</item>
	</channel>
</rss>
