<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Photography on Ning Yu's Blog</title><link>https://ningyu.cc/tags/photography/</link><description>Recent content in Photography on Ning Yu's Blog</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 03 Dec 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://ningyu.cc/tags/photography/index.xml" rel="self" type="application/rss+xml"/><item><title>Why Give Up Taking Videos?</title><link>https://ningyu.cc/posts/why-give-up-taking-videos/</link><pubDate>Wed, 03 Dec 2025 00:00:00 +0000</pubDate><guid>https://ningyu.cc/posts/why-give-up-taking-videos/</guid><description>&lt;p&gt;Honor released its new product, the Robot Phone, which features a stabilized camera. I was shocked when I saw this announcement because I believed that people mostly scan QR codes with their phone camera and only take videos to take evidence in conflicts. What made me even more shocked was the public&amp;rsquo;s positive attitude towards it.&lt;/p&gt;
&lt;p&gt;This article will argue that taking videos to record your trip is unnecessary and a burden on both your devices and your spirit, while offering little exposure, based on my experience with creating vlogs.&lt;/p&gt;</description></item><item><title>Limitations of AI - Changing the Background of Pictures</title><link>https://ningyu.cc/posts/limitations-of-ai/</link><pubDate>Tue, 04 Nov 2025 00:00:00 +0000</pubDate><guid>https://ningyu.cc/posts/limitations-of-ai/</guid><description>&lt;p&gt;As a member of Starry Gallery, I spare no effort in exploring editing photos with AI. However, through the practice of changing the backgrounds, several limitations have been discovered through these replacement works.&lt;/p&gt;
&lt;h2 id="pc-and-software"&gt;PC and Software&lt;/h2&gt;
&lt;p&gt;In case the same problems only happen on my hardware and software, I will provide some explanations of my setup. To complete the background change, I use Stable Diffusion as the AI tool. I believe that 16GB of RAM and 12GB of VRAM is the minimum requirements. To be capable of running the AI model, I use:&lt;/p&gt;</description></item></channel></rss>