<?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>AI on smcleod.net</title>
    <link>https://smcleod.net/series/ai/</link>
    <description>Recent content in AI on smcleod.net</description>
    <image>
      <title>smcleod.net</title>
      <url>https://smcleod.net/logo-painted-350.svg</url>
      <link>https://smcleod.net/logo-painted-350.svg</link>
    </image>
    <generator>Hugo -- 0.152.2</generator>
    <language>en-GB</language>
    <lastBuildDate>Wed, 11 Mar 2026 19:02:49 +1100</lastBuildDate>
    <atom:link href="https://smcleod.net/series/ai/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>SuperPrompter - Supercharge your text prompts for AI/LLM image generation</title>
      <link>https://smcleod.net/2024/03/superprompter-supercharge-your-text-prompts-for-ai/llm-image-generation/</link>
      <pubDate>Fri, 22 Mar 2024 00:00:00 +0000</pubDate>
      <guid>https://smcleod.net/2024/03/superprompter-supercharge-your-text-prompts-for-ai/llm-image-generation/</guid>
      <description>&lt;p&gt;&lt;a href=&#34;https://github.com/sammcj/superprompter&#34;&gt;SuperPrompter&lt;/a&gt; is a Python-based application that utilises the &lt;a href=&#34;https://huggingface.co/roborovski/superprompt-v1&#34;&gt;SuperPrompt-v1&lt;/a&gt; model to generate optimised text prompts for AI/LLM image generation (for use with Stable Diffusion etc&amp;hellip;) from user prompts.&lt;/p&gt;
&lt;p&gt;&lt;img alt=&#34;screenshot&#34; loading=&#34;lazy&#34; src=&#34;https://smcleod.net/2024/03/superprompter-supercharge-your-text-prompts-for-ai/llm-image-generation/superprompter-screenshot.jpg&#34;&gt;&lt;/p&gt;
&lt;p&gt;See &lt;a href=&#34;https://brianfitzgerald.xyz/prompt-augmentation/&#34;&gt;Brian Fitzgerald&amp;rsquo;s Blog&lt;/a&gt; for a detailed explanation of the SuperPrompt-v1 model and its capabilities / limitations.&lt;/p&gt;
&lt;!-- more --&gt;
&lt;h2 id=&#34;features&#34;&gt;Features&lt;/h2&gt;
&lt;ul&gt;
&lt;li&gt;Utilises the &lt;a href=&#34;https://huggingface.co/roborovski/superprompt-v1&#34;&gt;SuperPrompt-v1&lt;/a&gt; model for text generation.&lt;/li&gt;
&lt;li&gt;A basic (aka ugly) graphical user interface built with tkinter.&lt;/li&gt;
&lt;li&gt;Customisable generation parameters (max new tokens, repetition penalty, temperature, top p, top k, seed).&lt;/li&gt;
&lt;li&gt;Optional logging of input parameters and generated outputs.&lt;/li&gt;
&lt;li&gt;Bundling options to include or exclude pre-downloaded model files.&lt;/li&gt;
&lt;li&gt;Unloads the models when the application is idle to free up memory.&lt;/li&gt;
&lt;/ul&gt;
&lt;h2 id=&#34;prebuilt-binaries&#34;&gt;Prebuilt Binaries&lt;/h2&gt;
&lt;p&gt;Check &lt;a href=&#34;https://github.com/sammcj/superprompter/releases&#34;&gt;releases&lt;/a&gt; page to see if there are any prebuilt binaries available for your platform.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Llamalink - Ollama to LM Studio LLM Model Linker</title>
      <link>https://smcleod.net/2024/03/llamalink-ollama-to-lm-studio-llm-model-linker/</link>
      <pubDate>Thu, 21 Mar 2024 00:00:00 +0000</pubDate>
      <guid>https://smcleod.net/2024/03/llamalink-ollama-to-lm-studio-llm-model-linker/</guid>
      <description>This is a simple command-line tool that allows you to easily link Ollama models to LM Studio&amp;#39;s directory structure. It simplifies the process of symlinking Ollama models to LM Studio, making it convenient to use the models in both applications.</description>
    </item>
    <item>
      <title>Open source, locally hosted AI powered Siri replacement</title>
      <link>https://smcleod.net/2023/11/open-source-locally-hosted-ai-powered-siri-replacement/</link>
      <pubDate>Mon, 20 Nov 2023 01:00:00 +0000</pubDate>
      <guid>https://smcleod.net/2023/11/open-source-locally-hosted-ai-powered-siri-replacement/</guid>
      <description>Using an ESP32 S3 Box 3 with Willow, Home Assistant and Large Language Models (LLMs) create a locally hosted, offline, AI powered Siri / Alexa replacement.</description>
    </item>
    <item>
      <title>SDXL LoRA Training</title>
      <link>https://smcleod.net/2023/10/sdxl-lora-training/</link>
      <pubDate>Mon, 30 Oct 2023 20:00:00 +0000</pubDate>
      <guid>https://smcleod.net/2023/10/sdxl-lora-training/</guid>
      <description>A talk I gave to some peers on creating your own SDXL LoRA models from my tinkering around over the last few weeks.</description>
    </item>
    <item>
      <title>Introduction to AI and Large Language Models (LLMs)</title>
      <link>https://smcleod.net/2023/01/introduction-to-ai-and-large-language-models-llms/</link>
      <pubDate>Thu, 26 Jan 2023 01:00:00 +0000</pubDate>
      <guid>https://smcleod.net/2023/01/introduction-to-ai-and-large-language-models-llms/</guid>
      <description>A high level intro to LLMs that I&amp;#39;m writing for a few friends that are new to the concept. It is far from complete, definitely contains some errors and is a work in progress.</description>
    </item>
  </channel>
</rss>
