<h1 id="zmix-tooniverse-xl-ol5ux7e0q">zMix - TooniVerse XL</h1>Do you want a Dude only place? DudeDiffusion on <a rel="ugc" href="https://discord.gg/GC9cgBskex">Discord</a>!TooniVerse, now in PonyXL!It's been a while coming, and probably I am way to late for the party- but here it is. TooniVerse XL. The model is based on Pony XL, meaning that it prefers the "score" prompt:<pre><code>score_9, score_8_up, score_7_up, score_6_up, [etc]</code></pre>This merge is made using the following (Beta 1):<ul><li>AutismMix Pony</li><li>A custom mix of Animerge v3.1 and SeaArt Furry v1</li><li>AnimeConfettiTuneXL</li></ul>The following LORA:<ul><li>add-detail-xl</li><li>BetterBulge</li><li>Hotcha</li><li>BoxerHole Style</li><li>Asura Style</li><li>Legends of Runeterra</li></ul>Beta 2 consists out of:<ul><li>AutismMix Confetti</li><li>Animagine XL3.1</li><li>SeaArt Furry v1(more to come, mind = foggy)</li></ul>The following LORA have been merged:<ul><li>ExpressiveH</li><li>BetterBulge</li><li>Add-detail-XL</li><li>Legends of Runeterra</li><li>Vixon's Pony Style - Emotive</li><li>Vixon's Pony Style - Facialhair</li><li>Coral Island Style (Different epoch curtesy of Barracuda)</li></ul><h2 id="recommended-settings:-uuhd3f28l">Recommended settings:</h2>I've mainly tested the merge with the settings below- this is largely because I've done most of the process in ComfyUI. By all means experiment!<ul><li>Sampler: Euler A or DPM++ 2M Karras</li><li>Steps: 40 (beta 1), 30/40 (beta 2)</li><li>Hires Fix: 4x_NMKD-Superscale, 2x, 0.45 denoise</li><li>Size: 1156x896/896x1156, 1216x832/832x1216, 1200x1200</li><li>CFG: 7 / 8 (beta 1), 6/7 (beta 2)</li><li>Clipskip: 2 (though, not needed I have it set to 2 anyway)</li><li>VAE: baked in, but expierment</li><li>Adetailer: face_yolov8n_v2 and mediapike_face_mesh_eyes_only</li></ul><h2 id="known-quirks:-1qh9810k7">Known quirks:</h2><ul><li>The model at time really is keen on placing watermarks onto the pictures- I am assuming this is because of the data that Lora has been trained with; I will try to fix it in future versions. (Beta 1, Beta 2 does not have this issue)</li></ul><h2 id="special-thanks:-7atqcx503">Special Thanks:</h2><ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/user/TheHiddenOne">TheHiddenOne - For providing me with earlier Epochs of his model so I could merge his style into the Model.</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/user/invariable">Invariable - Still being an amazing tester and friend</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/user/Scratchproof">Scratchproof</a> - Testing the model and keeping me (in)sane with other mischief</li></ul>

zMix - TooniVerse XL

Different base existing of:<ul><li>AutismMix Confetti</li><li>Animagine XL 3.1</li><li>Furry XL 1.0</li></ul>Lora's:<ul><li>ExpressiveH</li><li>Add-Detail-XL</li><li>BetterBulge</li><li>Legends of Runeterra</li><li>Coral Island Style</li></ul>

zmixTooniverseXL_beta2.safetensors

Beta 2

Beta 1

zMix - TooniVerse XLTooniVerse, now in PonyXL!It's been a while coming, and probably I am way to late for the party- but here it is. TooniVerse XL. The model is based on Pony XL, meaning that it prefers the "score" prompt:score_9, score_8_up, score_7_up, score_6_up, [etc]This merge is made using the following (Beta 1):<ul><li>AutismMix Pony</li><li>A custom mix of Animerge v3.1 and SeaArt Furry v1</li><li>AnimeConfettiTuneXL</li></ul>The following LORA:<ul><li>add-detail-xl</li><li>BetterBulge</li><li>Hotcha</li><li>BoxerHole Style</li><li>Asura Style</li><li>Legends of Runeterra</li></ul>Beta 2 consists out of:<ul><li>AutismMix Confetti</li><li>Animagine XL3.1</li><li>SeaArt Furry v1(more to come, mind = foggy)</li></ul>The following LORA have been merged:<ul><li>ExpressiveH</li><li>BetterBulge</li><li>Add-detail-XL</li><li>Legends of Runeterra</li><li>Vixon's Pony Style - Emotive</li><li>Vixon's Pony Style - Facialhair</li><li>Coral Island Style (Different epoch curtesy of Barracuda)</li></ul>Recommended settings:I've mainly tested the merge with the settings below- this is largely because I've done most of the process in ComfyUI. By all means experiment!<ul><li>Sampler: Euler A or DPM++ 2M Karras</li><li>Steps: 40 (beta 1), 30/40 (beta 2)</li><li>Hires Fix: 4x_NMKD-Superscale, 2x, 0.45 denoise</li><li>Size: 1156x896/896x1156, 1216x832/832x1216, 1200x1200</li><li>CFG: 7 / 8 (beta 1), 6/7 (beta 2)</li><li>Clipskip: 2 (though, not needed I have it set to 2 anyway)</li><li>VAE: baked in, but expierment</li><li>Adetailer: face_yolov8n_v2 and mediapike_face_mesh_eyes_only</li></ul>Known quirks:<ul><li>The model at time really is keen on placing watermarks onto the pictures- I am assuming this is because of the data that Lora has been trained with; I will try to fix it in future versions. (Beta 1, Beta 2 does not have this issue)</li></ul>Special Thanks:<ul><li><a target="_blank" rel="ugc" href="https://civitai.com/user/TheHiddenOne">TheHiddenOne - For providing me with earlier Epochs of his model so I could merge his style into the Model.</a></li><li><a target="_blank" rel="ugc" href="https://civitai.com/user/invariable">Invariable - Still being an amazing tester and friend</a></li><li><a target="_blank" rel="ugc" href="https://civitai.com/user/Scratchproof">Scratchproof</a> - Testing the model and keeping me (in)sane with other mischief</li></ul>

Files with SHA256: dc0d103fdd94304ff4e1f75e66a14b879af2b9c0b5b78b32016aa5281ebe208e