<h2 id="designed-by-ktiseos-nyx.">Designed by Ktiseos Nyx.</h2>We're working hard at keeping up with what we enjoyed in SD 1.5 and beyond - the more we develop our models the more joy we see! EA's are only for 14 days and we'll try and release freebies between if at all possible.If you're interested in supporting us in our long standing AI journey please scroll down for ways to connect &amp; sponsor us!<h3 id="recommended-settings">✨ Recommended Settings</h3>To get the best out of ANY of our models, try these settings:<ul><li>Samplers: Euler or Euler Ancestral</li><li>Scheduler: Karras</li><li>Negative Prompt: Generally not needed! The model is designed to perform well without one, but feel free to experiment based on your preferences.</li><li>HiRes Fix:<ul><li>Steps: 15</li><li>Denoise: 0.3</li><li>Upscale: 2x</li></ul></li><li>Upscalers: Rex, 4x_Remacri, or your personal favorite.</li><li>ADetailer: Use sparingly. Due to potential VAE differences, it might occasionally produce grey squares.</li><li>Embeddings: We've used some of our own custom embeddings to showcase character types in our examples, but no stylistic embeddings were necessary to achieve the core look.</li><li>LoRA Compatibility: Chances are good that most LoRAs will work with this. However, be aware that while they will function, the result might not perfectly align with your expectations if the LoRA heavily influences style. It's a "What You See Is What You Get" situation with the base model's strong aesthetic – it'll likely produce a good image, just perhaps not the one you had in mind with a very specific LoRA.</li></ul><h3 id="merge-and-training-details">🛠️ Merge &amp; Training Details</h3>The backbone of any of our mixes are built upon numerous LoRAs, many of which were trained in-house by Ktiseos Nyx. We're always experimenting and creating! Due to the wonderfully rapid pace of Ktiseos Nyx's LoRA development, we confess that sometimes the exact lineage of merged checkpoints becomes a delightful mystery. We believe in training as much as we can ourselves, but the spirit of community and shared creation is vital!<ul><li>2.0 Now has a Baked in LUNAXL Vae - which i have yet to find come back to Civitai, so if you're the creator of that Vae, I THANK YOU A LOT! </li></ul><h3 id="acknowledgements">🙏 Acknowledgements</h3>A huge thank you to the incredible community members whose work and inspiration contribute so much. Special mentions to: Arthemy, Wai, Holostrawberry, FallenIncursio, RichyRich, JustTNP, Hoseki, CitronLegacy, Samael1976, Kairen92, ShadowxArt, Flyx3, YeiYeiart, LazyVisionary, and so many more! We try to train as much as we can ourselves, but the community's creativity is a constant source of inspiration.<h3 id="about-ktiseos-nyx-and-connect-with-us!">🌟 About Ktiseos Nyx &amp; Connect With Us!</h3>Ktiseos Nyx is available for commissions! Find us and more of our creations here:<ul><li>Discord: <a target="_blank" rel="ugc" href="https://discord.gg/HhBSvM9gBY">https://discord.gg/HhBSvM9gBY</a></li><li>Twitch: <a target="_blank" rel="ugc" href="https://twitch.tv/duskfallcrew">https://twitch.tv/duskfallcrew</a></li><li>Arc En Ciel: <a target="_blank" rel="ugc" href="https://arcenciel.io/users/77">https://arcenciel.io/users/77</a></li><li>X/Twitter: <a target="_blank" rel="ugc" href="https://x.com/KtiseosNyx_AI">https://x.com/KtiseosNyx_AI</a></li><li>Bluesky: <a target="_blank" rel="ugc" href="https://bsky.app/profile/duskfallcrew.bsky.social">https://bsky.app/profile/duskfallcrew.bsky.social</a></li><li>Sponsor Models &amp; Commissions: <a target="_blank" rel="ugc" href="https://ko-fi.com/duskfallcrew/commissions">https://ko-fi.com/duskfallcrew/commissions</a></li><li>Model Backups: <a target="_blank" rel="ugc" href="https://huggingface.co/EarthnDusk/">https://huggingface.co/EarthnDusk/</a></li><li>TensorArt Space: <a target="_blank" rel="ugc" href="https://tensor.art/u/611011406535381539">https://tensor.art/u/611011406535381539</a></li></ul><h3 id="licence-and-details">✨ Licence and Details</h3><ul><li>Outputs cannot be sold without further editing beyond color grading and basic resizing. </li><li>Monetary gain from outputs should only be used if further re-drawing has occured. </li><li>I am not and nor is Civitai, nor is Ktiseos Nyx as a whole responsible for any outputs that go against anything. </li><li>Plain English: It's up to you what you do, but if you get sued by Disney, that's your fault not mine :) </li></ul>

Ultra Comix IllustriousXL

ultraComix_v20.safetensors

v2.0

v1.5

v1.0

✨ Recommended SettingsTo get the best out of ANY of our models, try these settings:<ul><li>Samplers: Euler or Euler Ancestral</li><li>Scheduler: Karras</li><li>Negative Prompt: Generally not needed! The model is designed to perform well without one, but feel free to experiment based on your preferences.</li><li>HiRes Fix:<ul><li>Steps: 15</li><li>Denoise: 0.3</li><li>Upscale: 2x</li></ul></li><li>Upscalers: Rex, 4x_Remacri, or your personal favorite.</li><li>ADetailer: Use sparingly. Due to potential VAE differences, it might occasionally produce grey squares.</li><li>Embeddings: We've used some of our own custom embeddings to showcase character types in our examples, but no stylistic embeddings were necessary to achieve the core look.</li><li>LoRA Compatibility: Chances are good that most LoRAs will work with this. However, be aware that while they will function, the result might not perfectly align with your expectations if the LoRA heavily influences style. It's a "What You See Is What You Get" situation with the base model's strong aesthetic – it'll likely produce a good image, just perhaps not the one you had in mind with a very specific LoRA.</li></ul>🛠️ Merge &amp; Training DetailsThe backbone of any of our mixes are built upon numerous LoRAs, many of which were trained in-house by Ktiseos Nyx. We're always experimenting and creating! Due to the wonderfully rapid pace of Ktiseos Nyx's LoRA development, we confess that sometimes the exact lineage of merged checkpoints becomes a delightful mystery. We believe in training as much as we can ourselves, but the spirit of community and shared creation is vital!

Files with SHA256: e0d40ba60eebe92e11e973b479b49dc9499b6e79acad6710d8ff7b75f6975f3f