<h1 id="mary-ann-&quot;huckleberry&quot;-(green)">Mary-Ann "Huckleberry" (green)</h1>A fan-made Character LoRA for Mary-Ann "Huckleberry" from the comics by Jay Naylor.This version was trained specifically with PG / PG-13-friendly and SFW use in mind, so the goal was to create a version of the character that works well for Civit Green generation while still keeping her recognizable look and personality.If you're looking for a LoRA that can generate Mary-Ann reliably with just a simple prompt, this one should give you a very solid starting point.<hr /><h2 id="quick-info">✨ Quick Info</h2><ul><li>Character: Mary-Ann "Huckleberry"</li><li>Type: Character LoRA</li><li>Trigger word: <code>mary-ann-greenV1</code></li><li>Base architecture: Pony Diffusion</li><li>Training checkpoint: AutismMix SDXL (<code>AutismMix_pony</code>)</li><li>Recommended LoRA weight: <code>1.0</code></li></ul><hr /><h2 id="green-pg-13-focus">✅ Green / PG-13 Focus</h2>This LoRA was made with Green compatibility as a priority and is intended for PG / PG-13-style use only.That means this version focuses on:<ul><li>recognizable character likeness</li><li>flexible prompting</li><li>clean and usable outputs</li><li>compatibility with SFW generation workflows</li></ul><hr /><h2 id="recommended-settings">🚀 Recommended Settings</h2>These are the settings that worked best for me so far:<ul><li>LoRA weight: <code>1.0</code></li><li>Steps: <code>30</code></li><li>CFG: <code>7</code></li><li>Sampler: <code>DPM++ 2M Karras</code></li></ul>Since this is the first version, you can still experiment a bit, but <code>1.0</code> is currently the recommended default.<hr /><h2 id="trigger-prompting">🏷️ Trigger / Prompting</h2><h3 id="required-trigger:">Required trigger:</h3><code>mary-ann-greenV1</code>In most cases, the trigger word alone is already enough to generate the character quite well.You can improve consistency further by adding appearance tags when needed.<h3 id="helpful-optional-tags:">Helpful optional tags:</h3><ul><li><code>tanned skin</code></li><li><code>blonde long hair</code></li><li><code>twintails</code></li><li><code>low twintails</code></li><li><code>freckles</code></li><li><code>young face</code></li><li><code>wide hips</code></li><li><code>wide thighs</code></li><li><code>round breast</code></li><li><code>shiny skin</code></li></ul><h3 id="default-outfit:">Default outfit:</h3><ul><li><code>blue overalls</code></li><li><code>white t-shirt</code></li></ul><hr /><h2 id="default-appearance">👀 Default Appearance</h2>This LoRA is mainly trained around Mary-Ann's recognizable core look:<ul><li>tanned skin</li><li>long blonde hair</li><li>low twintails</li><li>freckles</li><li>young face</li><li>curvy build</li><li>shiny skin</li></ul>Her default outfit is:<ul><li>blue overalls</li><li>white t-shirt</li></ul>That said, the LoRA is not locked to one outfit only and can handle other clothing as well.<hr /><h2 id="what-works-well">🧪 What Works Well</h2>This LoRA performs especially well with:<ul><li>portraits</li><li>full body shots</li><li>multiple viewing angles</li><li>different poses</li><li>different outfits</li></ul>It should work nicely for both simple and more detailed character prompts, and in my testing it handles a good range of angles better than expected.<hr /><h2 id="known-weaknesses">⚠️ Known Weaknesses</h2>Current weak points:<ul><li>hands</li><li>extreme perspectives</li><li>multiple characters in one image</li></ul>So if a generation gets messy, those are the first things I would simplify.<hr /><h2 id="checkpoint-compatibility">🧩 Checkpoint Compatibility</h2>This LoRA was trained on:<ul><li>Pony Diffusion</li><li>AutismMix SDXL (<code>AutismMix_pony</code>)</li></ul>Other Pony-based checkpoints may also work, but I have not tested additional checkpoints yet, so feedback is very welcome if you try it on other models.<hr /><h2 id="example-prompts">📝 Example Prompts</h2><h3 id="1.-simple-portrait">1. Simple portrait</h3><pre><code>mary-ann-greenV1, (portrait), looking at viewer, tanned skin, blonde long hair, low twintails, freckles, young face, shiny skin, smiling, looking at viewer, brown background,</code></pre><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/bba1522d-2da8-4b66-951d-61b263ce1cf8/original=true/bba1522d-2da8-4b66-951d-61b263ce1cf8.jpeg" /><h3 id="2.-more-detailed-character-prompt">2. More detailed character prompt</h3><pre><code>mary-ann-greenV1, wearing green oversized sweater, white shorts, ((thigh high socks)), sitting on a wooden bench, background public park,</code></pre><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/2d23531f-d297-4309-a663-e1516942aa45/original=true/2d23531f-d297-4309-a663-e1516942aa45.jpeg" /><hr /><h2 id="final-notes">💬 Final Notes</h2>This is v1.0, and overall I'm very happy with how well it captures the character already.If you use it, feel free to share your generations and let me know:<ul><li>which checkpoint you used</li><li>what LoRA weight worked best for you</li><li>whether it stays consistent for your prompts</li><li>where it still struggles</li></ul>Feedback is always appreciated and will help improve future versions.Have fun with it!

Files with SHA256: 7a72e9fc48e9c1f7af62df4c06042a47a8c117dac0bcf59d796746cd6572e6d8