<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Images on Phil Wheat</title><link>https://philwheat.net/tags/images/</link><description>Recent content in Images on Phil Wheat</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 13 Oct 2026 09:05:00 -0500</lastBuildDate><atom:link href="https://philwheat.net/tags/images/index.xml" rel="self" type="application/rss+xml"/><item><title>Joy Caption Alpha Two</title><link>https://philwheat.net/links/joy-caption-alpha-two/</link><pubDate>Tue, 13 Oct 2026 09:05:00 -0500</pubDate><guid>https://philwheat.net/links/joy-caption-alpha-two/</guid><description>&lt;p&gt;JoyCaption is an image-captioning vision-language model built from the ground up to be free, open, and uncensored, aimed at generating captions for training diffusion models — fancyfeast&amp;rsquo;s claim is near-GPT-4o captioning quality while staying unrestricted. Alpha Two is the Llama-3.1-based iteration (LLaVA-style), with prompt-able caption formats (descriptive, Midjourney-style, art critic, product listing, tags) and 4-bit quantizations for low-VRAM cards. The linked HF Space is the hosted demo; ComfyUI custom nodes exist for local use.&lt;/p&gt;</description></item></channel></rss>