If the images are too dark for your taste put "dark theme" into the Negative prompt.<h3 id="v3-chenkinnoob:">V3-ChenkinNoob:</h3>New rebake of all styles used and then merged on the new <a target="_blank" rel="ugc" href="https://civarchive.com/models/2167995?modelVersionId=2441385">ChenkinNoob </a>since it has helped make the gens a lot cleaner.Note all previous illustrious-0.1 and NoobAi loras work perfectly fine from what I have tested on ChenkinNoob.If you are using Reforge WebUi turning on EPS scaling can help improve gens further, I personally also use FreeU for the samples above. Gen settings I use are the same as previous versions.Fixed some of the quirks from V2.2 but please do share if you find anything I may I have missed.<h3 id="my-generation-settings-for-v2-3:">My Generation Settings for V2-3:</h3><ul><li>Sampler: Euler A AYS</li><li>Sampling Steps: 24</li><li>Upscaler settings:<ul><li><a target="_blank" rel="ugc" href="https://openmodeldb.info/models/4x-UltraSharp">4x-UltraSharp</a> or <a target="_blank" rel="ugc" href="https://openmodeldb.info/models/4x-AnimeSharp">4x-AnimeSharp</a></li><li>1.5x - 2.0x Upscale</li><li>10 Hires steps</li><li>Denoise 0.1-0.6 (Use lower denoise on higher Upscale)</li></ul></li><li>Suggested Dimensions: 832x1216, 1216x832, or 1024x1024</li><li>CFG Scale: 4-6</li><li><a target="_blank" rel="ugc" href="https://github.com/Bing-su/adetailer">ADetailer </a>along with<a target="_blank" rel="ugc" href="https://huggingface.co/Anzhc/Anzhcs_YOLOs/blob/main/Anzhc%20Face%20seg%20640%20v3%20y11n.pt"> Anzhc's Face seg 640 v3 y11n</a><ul><li>Inpaint Denoise: 0.2-0.5</li><li>Use Separate width/height:<ul><li>1024x1024</li></ul></li><li>Inpaint mask blur: 24</li><li>Inpaint only masked padding, pixels: 48</li></ul></li><li>Positive prompt base:<ul><li>masterpiece, best quality,</li></ul></li><li>Negative prompt base:<ul><li>worst quality, low quality, bad anatomy, watermark </li></ul></li></ul><h3 id="v2.2:">V2.2:</h3>Extra re-merge using <a target="_blank" rel="ugc" href="https://civarchive.com/models/1365622/animusmix-v10">AnimusMix </a>as base and removed some of the other checkpoints, now its just <a target="_blank" rel="ugc" href="https://civarchive.com/models/941345/hoseki-lustrousmix-illustriousxlnoobai-eps11">LustrousMix</a><a target="_blank" rel="ugc" href="https://arcenciel.io/models/14"> </a>used as an extra mixed on <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1116447">NoobAi-Epsilon-1.1.</a>The finger issues from V2.1 have been much reduced and somehow after lots of mixing it came out even cleaner so I hope you all enjoy. Worst case use <code>fewer digits</code> in the negative for more finger stability.<h3 id="v2.1:">V2.1:</h3>Remerge using <a target="_blank" rel="ugc" href="https://civarchive.com/models/1365622/animusmix-v10">AnimusMix </a>as base and changed the other ckpts to <a target="_blank" rel="ugc" href="https://civarchive.com/models/941345/hoseki-lustrousmix-illustriousxlnoobai-eps11">LustrousMix </a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/1377342?modelVersionId=1556239">Garage Mix Noob</a> and <a target="_blank" rel="ugc" href="https://arcenciel.io/models/9327">MFCG's Soft Serve</a><a target="_blank" rel="ugc" href="https://arcenciel.io/models/14"> </a>on <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1116447">NoobAi-Epsilon-1.1.</a>Was noticing various finger and hand issues with blur and artifacts that bugged me so I went and tried to fix it. Should be a lot better and cleaner now but if anything is consistently odd please let me know.If you have some issues with fingers add <code>(fewer digits, 3 fingers:1.3)</code> to the negative and it should help until I update the model later.<h3 id="v2:">V2:</h3>Updated merge using <a target="_blank" rel="ugc" href="https://civarchive.com/models/1365622/animusmix-v10">AnimusMix </a>as base with some <a target="_blank" rel="ugc" href="https://civarchive.com/models/913998/noobaicyberfix">NoobaiCyberFix </a>and <a target="_blank" rel="ugc" href="https://arcenciel.io/models/14">MonsterCoffeeVenom!-Mix</a> on <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1116447">NoobAi-Epsilon-1.1.</a>Goal of V2 was to use Anzhc's new <a target="_blank" rel="ugc" href="https://huggingface.co/Anzhc/Anzhcs-VAEs/blob/main/SDXL%20Anime%20VAE%20Dec-only%20B3.safetensors">SDXL Anime VAE Dec-only B3</a> VAE which is baked into the model, I suggest to use this VAE or none as its baked in. Otherwise I wanted to make the mix cleaner and sharper with much better dark gens. Use: <code>Dark, dark theme, darkness</code> for general dark gens or <code>night, dim lighting</code> for light specific darkness.There are some mild quirks, if animal ears fail make sure to add <code>animal ears</code> tag to stabilize it. Sometime extra people leak into gens if you forget <code>solo</code>.Will fix most of the issues with a V3 but I need to remake and find more styles before I can do that.<h3 id="v1:">V1:</h3> Based on <a target="_blank" rel="ugc" href="https://civarchive.com/models/795765/illustrious-xl">Illustrious-XL</a> and <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1116447">NoobAi</a> so please visit that page for a rundown of prompts, tags and other baked in features. This model is a merge of Styles I baked and then mixed on <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1116447">NoobAi-Epsilon-1.1</a>. <h3 id="my-generation-settings-for-v1:">My Generation Settings for V1:</h3><ul><li>Sampler: Euler A AYS</li><li>Sampling Steps: 24</li><li>Upscaler settings:<ul><li><a target="_blank" rel="ugc" href="https://openmodeldb.info/models/4x-UltraSharp">4x-UltraSharp</a> or <a target="_blank" rel="ugc" href="https://openmodeldb.info/models/4x-AnimeSharp">4x-AnimeSharp</a></li><li>1.5x - 2.0x Upscale</li><li>10 Hires steps</li><li>Denoise 0.1-0.6 (Use lower denoise on higher Upscale)</li></ul></li><li>Suggested Dimensions: 832x1216, 1216x832, or 1024x1024</li><li>CFG Scale: 4-6 </li><li><a target="_blank" rel="ugc" href="https://github.com/Bing-su/adetailer">ADetailer </a>along with<a target="_blank" rel="ugc" href="https://huggingface.co/Anzhc/Anzhcs_YOLOs/blob/main/Anzhc%20Face%20seg%20640%20v3%20y11n.pt"> Anzhc's Face seg 640 v3 y11n</a><ul><li>Inpaint Denoise: 0.2-0.5</li><li>Use Seperate width/height:<ul><li>1024x1024</li></ul></li><li>Inpaint mask blur: 24</li><li>Inpaint only masked padding, pixels: 48 </li></ul></li><li>Positive prompt base:<ul><li>masterpiece, best quality,</li></ul></li><li>Negative prompt base:<ul><li>worst quality, low quality, bad anatomy, watermark </li></ul></li></ul>Important note: Baked in characters for illustrious/NoobAi are often burnt so you may need to reduce weight so it doesn't make the ckpt look strange.New merge to tickle a different craving I was having, spent some time improving my ability to train styles and used that to make the styles I merged into this model. I hope you all enjoy. Check out the samples above for inspiration and/or ideas.

Vermilion

V2 - Focus was on cleaning on the overall model and making dark gens very viable while improving sharpness by baking in Anzhc's new VAE that removes a lot of noise during generation. Style is somewhat different than V1 but that is due to issues with the old style bakes I had used for V1.

vermilion_v20.safetensors

v2.0

v3.1-ChenkinNoob-V0.2

v3.0-ChenkinNoob-V0.1

v2.2

v2.1

v1.0

Based on and so please visit that page for a rundown of prompts, tags and other baked in features. This model is a merge of Styles I baked and then mixed on . <h3 id="my-generation-settings-for-v1:-y60jajzgy">My Generation Settings for V1:</h3><ul><li>Sampler: Euler A AYS</li><li>Sampling Steps: 24</li><li>Upscaler settings:<ul><li> or </li><li>1.5x - 2.0x Upscale</li><li>10 Hires steps</li><li>Denoise 0.1-0.6 (Use lower denoise on higher Upscale)</li></ul></li><li>Suggested Dimensions: 832x1216, 1216x832, or 1024x1024</li><li>CFG Scale: 4-6 </li><li>along with<ul><li>Inpaint Denoise: 0.2-0.5</li><li>Use Seperate width/height:<ul><li>1024x1024</li></ul></li><li>Inpaint mask blur: 24</li><li>Inpaint only masked padding, pixels: 48 </li></ul></li><li>Positive prompt base:<ul><li>masterpiece, best quality,</li></ul></li><li>Negative prompt base:<ul><li>worst quality, low quality, bad anatomy, watermark </li></ul></li></ul>Important note: Baked in characters for illustrious/NoobAi are often burnt so you may need to reduce weight so it doesn't make the ckpt look strange.New merge to tickle a different craving I was having, spent some time improving my ability to train styles and used that to make the styles I merged into this model. I hope you all enjoy. Check out the samples above for inspiration and/or ideas.

V2 - Focus was on cleaning on the overall model and making dark gens very viable while improving sharpness by baking in Anzhc's new VAE that removes a lot of noise during generation. Also dark gen were a goal and should work a lot better now.

VAE is baked in so don't use other VAE unless you wish for a more blurry image.

Style is somewhat different than V1 but that is due to issues with the old style bakes I had used for V1.

Files with SHA256: 7b6dbe6a9fc29a8709eba7e93634a52e44f0f9fd033d035937df2b01ba2748b8