<h1 id="heading-2586">Western Animation Diffusion</h1><h2 id="heading-2587">Comicbook and Western Animation Style Model</h2>Do you like what I do? Consider supporting me on <a target="_blank" rel="ugc" href="https://www.patreon.com/Lykon275">Patreon</a> 🅿️ or feel free to <a target="_blank" rel="ugc" href="https://snipfeed.co/lykon">buy me a coffee</a> ☕. A ❤️, a kind comment or a review is greatly appreciated.<h3 id="heading-2">Purpose of this model</h3><ul><li>Train character loras where the dataset is mostly made of cartoon screencaps or comicbooks, allowing less style transfer and less overfitting.</li><li>Add variety to mixes.</li><li>Have an alternative to anime models when it comes to western stuff.</li><li>Not for western style lora training. Pretty good when used with western style loras (thanks @AnteMaxx), but needs weight adjusting, as it's already closer to the lora style probably. </li></ul><h3 id="heading-236">Suggested settings</h3><ul><li>Set the ETA Noise Seed Delta (ENSD) to 31337</li><li>Set CLIP Skip to 2</li><li>DISABLE face restore. It's terrible, never use it</li><li>Use negative prompts and embeddings that don't ruin the style</li><li>Use AnimeVideo or Foolhardy as upscalers in highres fix</li><li>Use ADetailer for far away shots or full body images to avoid blurred faces</li></ul><h3 id="heading-651">Brief history</h3>This was requested by a supporter and I also wanted to see if I was capable of doing it. It was a funny little project.

Files with SHA256: d20bc9d543b7d7d46a3ed7d91edc1880d8423f1a8a77dcf378801b5dbe211c3b