This is my flagship PaSanctuary (SDXL, IllustriousXL). I find it's in line with what the community on Civitai likes producing. It's pretty versatile while also having an artstyle that's unique in image generation. NSFW compatible. Check out my other Checkpoints.<h3 id="refer-to-the-version-details-for-changelog.-rw0o6srg7">Refer to the version details for Changelog. </h3><h2 id="v5:-9jzrpbobu">V5:</h2>This Checkpoint is trained on the awesome Basemodel <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1116447">NoobAI-XL V1.1</a>.The only prompt you ever need is this positive prompt:<pre><code>masterpiece, best quality, newest, absurdres, highres</code></pre>Default negative Prompt:<pre><code>worst quality, old, early, low quality, lowres, bad hands, mutated hands, greyscale</code></pre>Additional option for Style change are:<ul><li><code>realistic</code></li></ul>No need for any additional negatives. Anything else for tag related stuff, see Basemodel <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1116447">NoobAI-XL V1.1</a>.This model is designed to work with resources trained on NoobAI-XL V1.1. Other SDXL or pony resources may not work.I also recommend to use the Extension <a target="_blank" rel="ugc" href="https://github.com/Bing-su/adetailer">Adetailer</a>.Settings for generating Images for V5:<ul><li>Sampler: Euler a</li><li>Steps: 30</li><li>CFG 6.0</li><li>Base Resolution 1024x1024</li></ul>Recipe: Merge to Checkpoint: TCV Style LoRA Restart Illustrious-XL + <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1116447">NoobAI-XL V1.1</a>.No additional Merge with block weights, adjustment and clip/tenc.<h2 id="v4:-an37j73o7">V4:</h2>This Checkpoint is trained on the awesome Basemodel <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1116447">NoobAI-XL V1.1</a>.The only prompt you ever need is this positive prompt:<pre><code>masterpiece, best quality, newest, absurdres, highres</code></pre>Default negative Prompt:<pre><code>worst quality, old, early, low quality, lowres, bad hands, mutated hands, greyscale</code></pre>Additional option for Style change are:<ul><li><code>realistic</code>/ <code>3d</code></li></ul>No need for any additional negatives, except <code>realistic, 3d</code>, if the realism is bleeding in. Putting <code>3d</code> in negative prompt is mostly enough. Anything else for tag related stuff, see Basemodel <a target="_blank" rel="ugc" href="https://civarchive.com/models/795765/illustrious-xl">Illustrious-XL</a>.This model is designed to work with resources trained on Illustrious-XL-v0.1. Other SDXL or pony resources may not work.I also recommend to use the Extension <a target="_blank" rel="ugc" href="https://github.com/Bing-su/adetailer">Adetailer</a>.Settings for generating Images for V4:<ul><li>Sampler: Euler a</li><li>Steps: 24-30</li><li>CFG 5.0-6.0</li><li>Base Resolution 1024x1024</li></ul>If you have the Option, i would recommend this for Realism:<ul><li>Sampler: Restart</li><li>Scheduler type: SGM Uniform</li><li>Steps: 16-18</li><li>CFG 6.0</li><li>Base Resolution 1024x1024</li></ul>Recipe: Merge to Checkpoint: <a target="_blank" rel="ugc" href="https://civarchive.com/models/885394?modelVersionId=991101">TCV Style LoRA V4 Illustrious-XL</a> on Weight 0.6 + <a target="_blank" rel="ugc" href="https://civarchive.com/models/885394?modelVersionId=991101">TCV Style LoRA V2 Illustrious-XL</a> on Weight 0.3 + <a target="_blank" rel="ugc" href="https://civarchive.com/models/97089">night 黑夜概念</a> from @lchxi on Weight 0.4 + <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1116447">NoobAI-XL V1.1</a>.No additional Merge with block weights, adjustment and clip/tenc.<h2 id="v3:-qfy3ffymg">V3:</h2>This Checkpoint is trained on the awesome Basemodel <a target="_blank" rel="ugc" href="https://civarchive.com/models/795765/illustrious-xl">IllustriousXL</a>.The only prompt you ever need is this positive prompt:<pre><code>masterpiece, best quality</code></pre>Default negative Prompt:<pre><code>lowres, worst quality, low quality, bad anatomy, bad proportions, simple background,</code></pre>Additional option for Style change are:<ul><li><code>realistic</code>/ <code>3d</code></li></ul>No need for any additional negatives, except <code>realistic, 3d</code>, if the realism is bleeding in. Putting <code>3d</code> in negative prompt is mostly enough. Anything else for tag related stuff, see Basemodel <a target="_blank" rel="ugc" href="https://civarchive.com/models/795765/illustrious-xl">Illustrious-XL</a>.This model is designed to work with resources trained on Illustrious-XL-v0.1. Other SDXL or pony resources may not work.I also recommend to use the Extension <a target="_blank" rel="ugc" href="https://github.com/Bing-su/adetailer">Adetailer</a>.Settings for generating Images for V3:<ul><li>Sampler: Euler a</li><li>Steps: 24</li><li>CFG 6.0</li><li>Base Resolution 1024x1024</li></ul>If you have the Option, i would recommend this:<ul><li>Sampler: Restart</li><li>Scheduler type: SGM Uniform</li><li>Steps: 16-18</li><li>CFG 6.0</li><li>Base Resolution 1024x1024</li></ul>Recipe:Checkpoint Merge: PaSanctuary v2.5 (38%) + Nooabi v1.0 Epsilon (62%) Merge to Checkpoint: <a target="_blank" rel="ugc" href="https://civarchive.com/models/885394?modelVersionId=991101">TCV Style LoRA V2.5 Illustrious-XL</a> on Weight 0.8 + <a target="_blank" rel="ugc" href="https://civarchive.com/models/97089">night 黑夜概念</a> from @lchxi on Weight 0.55.Replaced CLIP G and CLIP L from <a target="_blank" rel="ugc" href="https://civarchive.com/models/510261/spo-sdxl4k-p10eplorawebui">SPO </a>and merged into Checkpoint.<h2 id="v2.5:-25xdwibhw">V2.5:</h2>This Checkpoint is trained on the awesome Basemodel <a target="_blank" rel="ugc" href="https://civarchive.com/models/795765/illustrious-xl">IllustriousXL</a>.The only prompt you ever need is this positive prompt:<pre><code>masterpiece, best quality</code></pre>Default negative Prompt:<pre><code>lowres, worst quality, low quality, bad anatomy, bad proportions, extra limbs, extra digit, extra legs, extra legs and arms, disfigured, missing arms, too many fingers, fused fingers, missing fingers, unclear eyes, username, simple background,</code></pre>Anything else for tag related stuff, see Basemodel <a target="_blank" rel="ugc" href="https://civarchive.com/models/795765/illustrious-xl">Illustrious-XL</a>.This model is designed to work with resources trained on Illustrious-XL-v0.1. Other SDXL or pony resources may not work.I also recommend to use the Extension <a target="_blank" rel="ugc" href="https://github.com/Bing-su/adetailer">Adetailer</a>.Settings for generating Images for V2.5:<ul><li>Sampler: Euler a</li><li>Steps: 24</li><li>CFG 6.0</li><li>Base Resolution 1024x1024</li></ul>If you have the Option, i would recommend this:<ul><li>Sampler: Restart</li><li>Scheduler type: SGM Uniform</li><li>Steps: 16-18</li><li>CFG 6.0</li><li>Base Resolution 1024x1024</li></ul>Recipe: Merge to Checkpoint: <a target="_blank" rel="ugc" href="https://civarchive.com/models/885394?modelVersionId=991101">TCV Style LoRA V2.5 Illustrious-XL</a> on Weight 1.0 + <a target="_blank" rel="ugc" href="https://civarchive.com/models/97089">night 黑夜概念</a> from @lchxi on Weight 1.0 + <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1022833">NoobAI-XL V1 (NAI-XL)</a>.No additional Merge with block weights, adjustment and clip/tenc.This ckpt is now under Fair-AI-Public-License-1.0-SD.<h2 id="v2:-62w6hd7c3">V2:</h2>This Checkpoint is trained on the awesome Basemodel <a target="_blank" rel="ugc" href="https://civarchive.com/models/795765/illustrious-xl">IllustriousXL</a>. The only prompt you ever need is this positive prompt:<pre><code>masterpiece, best quality</code></pre>Additional option for Style change are:<ul><li><code>anime</code></li><li><code>realistic</code></li></ul>Default negative Prompt:<pre><code>lowres, worst quality, low quality, bad anatomy, bad proportions, extra limbs, extra digit, extra legs, extra legs and arms, disfigured, missing arms, too many fingers, fused fingers, missing fingers, unclear eyes, username, simple background,</code></pre>No need for any additional negatives, except <code>realistic, 3d</code>, if the realism is bleeding in, despite prompting <code>anime</code>. Anything else for tag related stuff, see Basemodel <a target="_blank" rel="ugc" href="https://civarchive.com/models/795765/illustrious-xl">Illustrious-XL</a>.This model is designed to work with resources trained on Illustrious-XL-v0.1. Other SDXL or pony resources may not work.I also recommend to use the Extension <a target="_blank" rel="ugc" href="https://github.com/Bing-su/adetailer">Adetailer</a>.Settings for generating Images for V2:<ul><li>Sampler: Euler a</li><li>Steps: 24</li><li>CFG 6.0</li><li>Base Resolution 1024x1024</li></ul>Recipe: Merge to Checkpoint: <a target="_blank" rel="ugc" href="https://civarchive.com/models/885394?modelVersionId=991101">TCV Style LoRA Illustrious-XL</a> on Weight 1.0 + <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=968495">NoobAI-XL V0.5 (NAI-XL)</a>.No additional Merge with block weights and adjustment.This ckpt is now under Fair-AI-Public-License-1.0-SD.<h2 id="v1:-trsguzi4q">V1:</h2>This Checkpoint is trained on the awesome Basemodel <a target="_blank" rel="ugc" href="https://civarchive.com/models/795765/illustrious-xl">IllustriousXL</a>.This is in Collaboration with @Anzhc. Check out his <a target="_blank" rel="ugc" href="https://civarchive.com/models/353543/aaaautism-or-pony-finetune-mix">AAAAAAAAAAAAAA.</a>😉The only prompt you ever need is this positive prompt:<pre><code>masterpiece, best quality</code></pre>Default negtive Prompt:<pre><code>lowres, worst quality, low quality, bad anatomy, bad hands, 4koma, comic, greyscale, jpeg artifacts, overly saturated, overly vivid</code></pre>No need for any additional negatives, except <code>realistic, 3d</code>, if you want to change the style. Please dont use any or at least only use negatives, that you dont want in your current image. I'm sick of seeing schizo negatives and schizo positives. Anything else for tag related stuff, see Basemodel <a target="_blank" rel="ugc" href="https://civarchive.com/models/795765/illustrious-xl">Illustrious-XL</a>.This model is designed to work with resources trained on Illustrious-XL-v0.1. Other SDXL or pony resources may not work.I also recommend to use the Extension <a target="_blank" rel="ugc" href="https://github.com/Bing-su/adetailer">Adetailer</a>.Settings for generating Images for V1:<ul><li>Sampler: Euler a</li><li>Steps: 24</li><li>CFG 6.0</li><li>Base Resolution 1024x1024</li></ul>Recipe V1: Merge to Checkpoint: TC V Style LoRA Illustrious-XL on Weight 0.8 + <a target="_blank" rel="ugc" href="https://civarchive.com/models/795765/illustrious-xl">Illustrious-XL</a>.Additional Merge with block weights and adjustment: PaSanctuary_v0.5 x (1-alpha) + PaSanctuary_v0.5 x alpha (0.2,0.017,0.434,0.052,0.485,0.038,0.652,0.206,0.421,0.032,0.144,0.073,0.27,0.249,0.331,0.849,0.653,0.847,0.979,0.065,0)Adjustment: -0.38,0.55,0,0.59,-2.74,0,0,0.92 Everything else is specified in the image tags. Make sure to leave a review or a comment if you got good use out of this Mix. How to use Checkpoints's in auto1111:<ul><li>Download Checkpoint</li><li>Copy the file to <code>stable-diffusion-webui/models/Stable-diffusion</code></li><li>Select your Checkpoint</li><li>Have Fun!</li></ul>

PaSanctuary (SDXL, IllustriousXL)

<ul><li>Merged into NoobAi</li><li>Retrained with more data</li><li>Trained as LoCON instead of LoRA</li><li>added much longer training time and steps</li><li>now with proper adjustment to <code>realistic</code> and <code>anime</code>, but can still bleed</li></ul>

Files with SHA256: 584347c64e0e62474212a767e68f08ed309aea74bf0c3feebbada36e8dee6203