<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Stable-Diffusion on blog.iankulin.com</title><link>https://blog.iankulin.com/tags/stable-diffusion/</link><description>Recent content in Stable-Diffusion on blog.iankulin.com</description><generator>Hugo</generator><language>en-AU</language><lastBuildDate>Tue, 11 Oct 2022 00:00:00 +0000</lastBuildDate><atom:link href="https://blog.iankulin.com/tags/stable-diffusion/index.xml" rel="self" type="application/rss+xml"/><item><title>Using AI to Generate Icons</title><link>https://blog.iankulin.com/using-ai-to-generate-icons/</link><pubDate>Tue, 11 Oct 2022 00:00:00 +0000</pubDate><guid>https://blog.iankulin.com/using-ai-to-generate-icons/</guid><description>&lt;p&gt;Since I have minimal design skills, I went back to &lt;a href="https://www.fiverr.com/"&gt;Fiverr&lt;/a&gt; (the digital gig economy platform) to get some icons done for CodeTrimmer - explaining that I wanted something like a &amp;ldquo;pair of scissors floating over some computer code&amp;rdquo;. At the same time I&amp;rsquo;ve been playing with &lt;a href="https://github.com/divamgupta/diffusionbee-stable-diffusion-ui"&gt;DiffusionBee&lt;/a&gt; - a free Apple silicon version of the &lt;a href="https://stability.ai/blog/stable-diffusion-public-release"&gt;Stable Diffusion&lt;/a&gt; artifical intellligence that generates images from text prompts. The image above was created on an M1 Macbook using DiffusionBee.&lt;/p&gt;
&lt;p&gt;Since generating an image from a text prompt is exactly what I&amp;rsquo;d just done with Fiverr, I thought I&amp;rsquo;d give the AI a chance. Even if the results are not great, they will do for the toy applications I&amp;rsquo;m creating as I&amp;rsquo;m learning.&lt;/p&gt;
&lt;p&gt;The model in Stable Diffusion is trained on images scraped from the internet, so it&amp;rsquo;s strong on pop culture and painting styles. For instance &amp;ldquo;Jack Black as Aquaman&amp;rdquo; is likely to give good results, also &amp;ldquo;Kermit dressed as Yoda in front of a sunset landscape&amp;rdquo;. The license for the outputs of the AI is quite permissive, including for commercial purposes as long as it&amp;rsquo;s not used for evil (that&amp;rsquo;s my paraphrasing, the actual &lt;em&gt;CreativeML Open RAIL-M&lt;/em&gt; license is &lt;a href="https://github.com/CompVis/stable-diffusion/blob/main/LICENSE"&gt;here&lt;/a&gt;).&lt;/p&gt;
&lt;p&gt;Here&amp;rsquo;s a couple of outputs for the different versions of the &amp;ldquo;scissors floating over code, macOS, icon&amp;rdquo; prompt.&lt;/p&gt;
&lt;p&gt;&lt;img src="https://blog.iankulin.com/images/screen-shot-2022-10-05-at-10.56.41-am.jpg" alt="screen cap of stable diffusion output"&gt;&lt;/p&gt;
&lt;p&gt;&lt;img src="https://blog.iankulin.com/images/screen-shot-2022-10-05-at-10.35.25-am.jpg" alt="screen cap of stable diffusion output"&gt;&lt;/p&gt;
&lt;p&gt;&lt;img src="https://blog.iankulin.com/images/kermit-dressed-as-yoda-in-front-of-a-sunset-landscape.jpg" alt="Kermit dressed as Yoda - Stable Diffusion"&gt;&lt;/p&gt;
&lt;p&gt;Like any tool, there is a skill to using it well, and with image generation from text prompts, the skill is in creating the prompts, hence a sudden plethora of articles about this all over the internet, and even a &lt;a href="https://promptbase.com/"&gt;market&lt;/a&gt; for them. So perhaps with a bit more skill I&amp;rsquo;d get something closer to what I&amp;rsquo;d like, although if you are prepared to accept something a bit abstract a couple of these would be fine.&lt;/p&gt;
&lt;p&gt;If I had a small amount of design skills these images might serve as a great creative thinking starting point - for example I like the criss-crossy background of one to represent code. I like the drop shadow and flat green of the ipod shuffle one - so these ideas could be combined to make a pair of flat green handled scissors floating over the lined background.&lt;/p&gt;
&lt;p&gt;If you are not allowed to use AI&amp;rsquo;s for evil (I&amp;rsquo;m looking at you &lt;a href="https://en.wikipedia.org/wiki/Skynet_(Terminator)"&gt;Skynet&lt;/a&gt;), it seems like using them as a tool for creating okay images for apps and other digital content is likely to become a practical use for them.&lt;/p&gt;</description></item></channel></rss>