Default rules as for any other Illustrious model:<ul><li>"explicit" keyword for 18+ content, "sensitive" for questionable, and "general" for default SFW content.</li><li>Use quality tags like "good qulity, best quality, etc." at the end of your prompt.</li></ul>The model supports this LCM lora partially (give it smaller weights if you see strange artifacts): <a target="_blank" rel="ugc" href="https://civarchive.com/models/216190/lcmandturbomix-lora-only-12mb-8-step-sampling-effect-is-superior-to-using-lcm-or-turbo-alone">https://civarchive.com/models/216190/lcmandturbomix-lora-only-12mb-8-step-sampling-effect-is-superior-to-using-lcm-or-turbo-alone</a>So you can generate images in around 12 steps by using this lora, euler_a_cfg++ sampler and sgm_uniform (faster) scheduler. You can use normal scheduler, which provides better quality with ~15 steps. It's mix of 3 models: <a target="_blank" rel="ugc" href="https://civarchive.com/models/926443?modelVersionId=1061268">https://civarchive.com/models/926443?modelVersionId=1061268</a> - NTRMix 4.0 (for some part of it's style) <a target="_blank" rel="ugc" href="https://civarchive.com/models/811067?modelVersionId=1015877">https://civarchive.com/models/811067?modelVersionId=1015877</a> - can't remember exact version. The model was used to get less annoying traits from loras that was used in NTRMix + small quality improvements<a target="_blank" rel="ugc" href="https://civarchive.com/models/950531?modelVersionId=1064213">https://civarchive.com/models/950531?modelVersionId=1064213</a> - RouWei. Good but unstable model. It improves knowledge of some rare tags. Also it gives more diversity in results.

3R Mix (Illustrious)

3rMixIllustrious_v10.safetensors

v1.0

Default rules as for any other Illustrious model:<ul><li>"explicit" keyword for 18+ content, "sensitive" for questionable, and "general" for default SFW content.</li><li>Use quality tags like "good qulity, best quality, etc." at the end of your prompt.</li></ul>The model supports this LCM lora partially (give it smaller weights if you see strange artifacts): <a target="_blank" rel="noopener noreferrer nofollow" href="https://civitai.com/models/216190/lcmandturbomix-lora-only-12mb-8-step-sampling-effect-is-superior-to-using-lcm-or-turbo-alone">https://civitai.com/models/216190/lcmandturbomix-lora-only-12mb-8-step-sampling-effect-is-superior-to-using-lcm-or-turbo-alone</a>So you can generate images in around 12 steps by using this lora, euler_a_cfg++ sampler and sgm_uniform (faster) scheduler. You can use normal scheduler, which provides better quality with ~15 steps.It's mix of 3 models: <a target="_blank" rel="noopener noreferrer nofollow" href="https://civitai.com/models/926443?modelVersionId=1061268">https://civitai.com/models/926443?modelVersionId=1061268</a> - NTRMix 4.0 (for some part of it's style) <a target="_blank" rel="noopener noreferrer nofollow" href="https://civitai.com/models/811067?modelVersionId=1015877">https://civitai.com/models/811067?modelVersionId=1015877</a> - can't remember exact version. The model was used to get less annoying traits from loras that was used in NTRMix + small quality improvements<a target="_blank" rel="noopener noreferrer nofollow" href="https://civitai.com/models/950531?modelVersionId=1064213">https://civitai.com/models/950531?modelVersionId=1064213</a> - RouWei. Good but unstable model. It improves knowledge of some rare tags. Also it gives more diversity in results.

Files with SHA256: 10f129c4fb770501906d36c9fd2d03f7b3eb89adb729c299ce06a02d84e2f8eb