<h1>Filmation's Masters of the Universe Style</h1> Features a wide variety: humans, creatures, dragons, aliens, landscapes, forests, and architecture in the specific style of Filmation's Masters of the Universe. I grew up watching this show and being mystified by the story line around Castle Grayskull. Enjoy! &gt; 🌟 This LoRA in an upgrade from the <a target="_blank" rel="ugc" href="https://civarchive.com/models/3162/filmation-motu-diffusion">original Dreambooth checkpoint</a><h2>Improvements over CKPT version</h2><ul><li>File size: 36.1MB vs 3.82GB</li><li>Text encoder trained on DeepBorru tags: <a target="_blank" rel="ugc" href="https://danbooru.donmai.us/tags">https://danbooru.donmai.us/tags</a></li><li>Additional training input: dragons, tigers, landscapes, architecture, emotion, clothing - see gallery for prompt examples.</li></ul><h2>Model Usage</h2>Trained using kohya-ss <a target="_blank" rel="ugc" href="https://github.com/kohya-ss/sd-scripts">SD scripts</a>.Using the <a target="_blank" rel="ugc" href="https://github.com/kohya-ss/sd-webui-additional-networks">Additional Networks</a> extension within Auto1111 is recommended as you can adjust UNet and Text Encoder weights independently.<h3>Cartoon Style</h3>Use any NAI or animation/cartoon type model trained with booru tagging:<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/AdamOswald1/Anything-Preservation">Anything V3</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/WarriorMama777/OrangeMixs">OrangeMixs</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/3627/protogen-v22-anime-official-release">Protogen v2.2 (Anime)</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/syaimu/7th_Layer">7th_Layer</a></li></ul> Weight: <code>0.1</code> - <code>0.9</code> Clip Skip: <code>2</code>&gt; 💥 VAE Check: Double check to make sure you're using the correct VAE per model. Having a VAE active (especially the correct one) will give you the best results. <h3>Realistic Style</h3>The style can transfer as LoRA weights to other models. Below are a few that I used to generate the sample images.<ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/2747/elldreths-vivid-mix">Elldreth's Vivid Mix</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/4823/deliberate">Deliberate</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/3666/protogen-x34-photorealism-official-release">Protogen x3.4</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/1366/elldreths-lucid-mix">Elldreth's Lucid Mix</a></li></ul> Weight: <code>0.1</code> - <code>0.55</code> Upscaler: <code>R-ESRGAN 4x+</code> Denoising strength: <code>0.5</code> - <code>0.63</code> <h3>img2img Settings</h3>This loRA was extensively tested with a large variety of img2img results. See various img2img samples in the Gallery.Denoising Strength: <code>0.58</code> CFG: <code>8</code> Steps: <code>20</code> LoRA Weight: <code>0.7</code>

Files with SHA256: 1faf8eb81936aa5dd3c64bd748d8a7b5b219d607e09abc1ded32cc5a6fdd552b