<p>전우애 실시!</p><p></p><h3 id="comradeshipxl-v14f">comradeshipXL-v14F</h3><p><span style="background-color:rgb(26, 27, 30);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">This model is a merger of the Comradeship XL v14VZ model and the Experimental NoobAI with Rectified Flow + EQ-VAE model. (</span><a target="_blank" rel="ugc" href="https://civarchive.com/models/2071356?modelVersionId=2343811"><span style="background-color:rgb(26, 27, 30);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">https://civarchive.com/models/2071356?modelVersionId=2343811</span></a><span style="background-color:rgb(26, 27, 30);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">)</span></p><p><br /><span style="background-color:rgb(26, 27, 30);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">This model requires Rectified Flow. </span><strong>YOU NEED TO USE COMFYUI/SWARMUI or any webui that can do ModelSamplingSD3 at 2.5</strong></p><p></p><h3 id="comradeshipxl-v14vww">comradeshipXL-v14VWW</h3><p>Comradeship XL v14VW3 × WAI-NSFW-illustrious-SDXL v15 Karcher-merge V-pred model</p><p></p><h3 id="comradeshipxl-v14kd2">comradeshipXL-v14KD2</h3><p>This is a minor update model of comradeshipXL-v14KC.</p><p></p><h3 id="comradeshipxl-v14vw2-v14vw3">comradeshipXL-v14VW2 / v14VW3</h3><p>A V-Pred merge model with slightly improved natural language prompt performance using Karcher-merge. (<a target="_blank" rel="ugc" href="https://github.com/win10ogod/Karcher-merge">https://github.com/win10ogod/Karcher-merge</a>)</p><p></p><h3 id="comradeshipxl-v14kc">comradeshipXL-v14KC</h3><p>The base SDXL model is a 1:1 mix of ILXL 2.0 and NoobAI EPS 1.1. This is a specialized model for high resolutions of 1.5K~1.75K.</p><p></p><h3 id="comradeshipxl-v14vx">comradeshipXL-v14VX</h3><p>As a model focused on improving the performance of high-resolution generation in NoobAI-based models, the supported resolutions for this model are not landscape, with a recommended 1536x1536 (1.5K) / up to 1796x1796 (1.75K).</p><p></p><h3 id="comradeshipxl-v14k1ax">comradeshipXL-v14K1AX</h3><p>Improved high-resolution generation performance based on v14K1A model.</p><p></p><h3 id="comradeshipxl-v14k1a">comradeshipXL-v14K1A</h3><p>A variant of Illustrious XL 1.1 from Comradeship XL v14.</p><h3 id="comradeshipxl-v17t4">comradeshipXL-v17T4</h3><p>comradeshipXL-v17T3 + ((comradeshipXL-v14K3 - Illustrious XL 0.1) * 0.5) = comradeshipXL-v17T4</p><p></p><h3 id="comradeshipxl-v14k3">comradeshipXL-v14K3</h3><p>Merged noobai-XL EPS 1.1 while retaining the 1536x1536 high-resolution capabilities of Illustrious-XL 1.0.</p><p></p><h3 id="comradeshipxl-v17t3">comradeshipXL-v17T3</h3><p>Animagine XL 4.0 Opt + mann-e-004 LoRA = comradeshipXL-v17T3</p><p></p><h3 id="comradeshipxl-v17t1">comradeshipXL-v17T1</h3><p>Animagine XL 4.0 + mann-e-004 LoRA = comradeshipXL-v17T1</p><p></p><h3 id="comradeshipxl-v14k">comradeshipXL-v14K</h3><p>Illustrious XL 1.0 version of <a target="_blank" rel="ugc" href="https://huggingface.co/hanzogak/comradeshipXL/blob/main/comradeshipXL-v14.safetensors">Comradeship XL v14</a></p><p></p><h3 id="comradeshipxl-v14v">comradeshipXL-v14V</h3><p>This is a minor update model of Comradeship XL v14T15V. Changed NoobAI XL V-Pred 0.75s to NoobAI XL V-Pred 1.0 in merge recipe for Comradeship XL v14T15V model. Since it is not a general SDXL (eps-prediction) model, it must be used in a v-prediction support program.</p><p></p><h3 id="comradeshipxl-v14vt">comradeshipXL-v14VT</h3><p>SDXL Hyper version of Comradeship XL v14V. Available in 6~15 steps / CFG 1.0 settings. Using the recommended settings, you can create images quickly.</p><p></p><h3 id="comradeshipxl-v14t15v">comradeshipXL-v14T15V</h3><p>This is a minor update model of Comradeship XL v14T14V. In v14T14V, I changed the base model to NoobAI XL V-Pred 0.75s and merged the differences from CLIP-SAE-ViT-L-14 - CLIP-ViT-L-14. Since it is not a general SDXL (eps-prediction) model, it must be used in a v-prediction support program.</p><p></p><h3 id="comradeshipxl-v14t14vv3">comradeshipXL-v14T14V/V3</h3><p>This is a v-prediction model based on NoobAI XL V-Pred 0.5 / 0.65s</p><p>Since it is not a general SDXL (eps-prediction) model, it must be used in a v-prediction support program.</p><p></p><p>This model recommends using Euler CFG++ and CFG is recommended between 1 and 2.5. A minimum of 8 steps is required, and 12 to 14 steps are recommended.</p><p></p><h3 id="comradeshipxl-v14t13ab">comradeshipXL-v14T13A/B</h3><p>In the merge recipe for the <a target="_blank" rel="ugc" href="https://huggingface.co/hanzogak/comradeshipXL/blob/main/comradeshipXL-v14T13.safetensors">Comradeship XL v14T13</a> model, I changed from the NoobAI-XL Early Access version to the NoobAI-XL 0.5/0.75 version.</p><p></p><h3 id="comradeshipxl-v14t1s">comradeshipXL-v14T1S</h3><p>This model is based on Illustrious-XL v0.1.</p><p>Merge recipes can be found at this link.</p><p><a target="_blank" rel="ugc" href="https://huggingface.co/hanzogak/comradeshipXL/tree/main/CSv14T1S-KIT">https://huggingface.co/hanzogak/comradeshipXL/tree/main/CSv14T1S-KIT</a></p><p></p><h3 id="comradeshipxl-v9mb4">comradeshipXL-v9MB4</h3><p>Anime performance has been slightly improved.</p><p></p><p>Check the ComfyUI EXIF of the models for details on how to merge.</p><p>v9B2-Lite6 → v9M6K → v9MF4 → v9MB4</p><p><a target="_blank" rel="ugc" href="https://huggingface.co/hanzogak/comradeshipXL/tree/main">https://huggingface.co/hanzogak/comradeshipXL/tree/main</a></p><p></p><h3 id="comradeshipxl-v9mb">comradeshipXL-v9MB</h3><p>Hard NSFW performance has been improved.</p><p><br />Check the ComfyUI EXIF ​​of the models for details on how to merge.</p><p><a target="_blank" rel="ugc" href="https://huggingface.co/hanzogak/comradeshipXL/tree/main">https://huggingface.co/hanzogak/comradeshipXL/tree/main</a></p><p>v9B2-Lite3 → v9M3 → v9M3K → v9MF → v9MB</p><p></p><h3 id="comradeshipxl-v9m">comradeshipXL-v9M</h3><p>The v9M model is a hybrid Pony model that has the character/artist features of the anime SDXL model. Features may not be as clear compared to purebred models.</p><p></p><p>InterDiffusion-4.0 - SDXL 1.0 = InterDiffusion-4.0 LoRA</p><p>Kohaku-XL Epsilon rev1 - kohaku-xl-epsilon-lyco = dummy2</p><p>Kohaku-XL Epsilon rev3 - dummy2 = Epsilon_dummy2 LoRA</p><p>comradeshipXL-v9AA-SPO-DPO-Flash-MaPObeta + mapo-safe LoRA + mann-e-004 LoRA + (InterDiffusion-4.0 × -1) + (Epsilon_dummy2 LoRA × -1) + marine-animeXL-290001 LoRA = comradeshipXL-v9AD2-Lite</p><p>Kohaku-XL Epsilon rev3 + mann-e-004 LoRA + SPO LoCon + DPO LoRA + mapo-safe LoRA + mapo-beta LoRA = comradeshipXL-v10T1</p><p>comradeshipXL-v10T1 + marine-animeXL-290001 LoRA = comradeshipXL-v10T3</p><p>Neta Art XL v2 + mann-e-004 LoRA + SPO LoCon + DPO LoRA + mapo-safe LoRA + mapo-beta LoRA = comradeshipXL-v11T1</p><p>comradeshipXL-v10T3 × 0.33 + comradeshipXL-v11T1 × 0.33 + comradeshipXL-v9AD2-Lite × 0.34 = comradeshipXL-v9B2-Lite</p><p>comradeshipXL-v9B2-Lite - SDXL 1.0 = CSv9B2-Lite LoRA</p><p>CSv9B2-Lite × 0.4 Unet + AAAAutism AAAA Restart × 0.6 Unet + CSv9B2-Lite TE + CSv9B2-Lite LoRA × 0.35 = comradeshipXL-v9M</p><p></p><h3 id="comradeship-xl-version-12-test-1-and-test-3">Comradeship XL Version 12 Test 1 &amp; Test 3</h3><p>CFG 4~6 / euler ascestral / beta</p><p>This model is a merge model based on wdv-test-v0.1 from <a target="_blank" rel="ugc" href="https://huggingface.co/waifu-diffusion/wdv-tests">wdv-tests</a>.</p><p><a target="_blank" rel="ugc" href="https://gist.github.com/neggles/ecb6327251a9e274428d07636c727eb9">ModelSamplingWaifuDiffusionV</a> is required. (ComfyUI ONLY!)</p><p>wdv-test-v0.1 - Animagine 3.1 = wdv01 LoRA (Unet only)</p><p>Mann-E_Dreams-0.0.4 - SDXL 1.0 = mann-e-004 LoRA (Unet only)</p><p>wdv-test-v0.1 + mann-e-004 LoRA × 0.75 + wdv01 LoRA × (-0.01) = comradeshipXL-v12T1-WDV01</p><p>ArtiWaifu Diffusion - SDXL 1.0 = ArtiWaifu LoRA</p><p>wdv-test-v0.1 + mann-e-004 LoRA × 0.75 + ArtiWaifu LoRA × 0.6 = comradeshipXL-v12T3-WDV01</p><p></p><h3 id="comradeshipxl-v9aa-spo-dpo-flash-mapobeta">comradeshipXL-v9AA-SPO-DPO-Flash-MaPObeta</h3><p>In this version, mapo-beta LoRA has been additionally merged in v9A.</p><p></p><h3 id="comradeshipxl-v9a-spo-dpo-flash">comradeshipXL-v9A-SPO-DPO-Flash</h3><p>This version merges SPO, DPO, and Flash's LoRA.</p><p>kivotos-xl-2.0 unet × 0.5 + autismmixSDXL_autismmixConfetti unet × 0.5 + kivotos-xl-2.0 Text Encoder = comradeshipXL-v7T10</p><p>comradeshipXL-v9T4 × 0.5 + comradeshipXL-v7T10 × 0.5 = comradeshipXL-v9T13</p><p>comradeshipXL-v9T13 + SPO LoCon+ DPO LoRA + Flash LoRA × 0.55 = comradeshipXL-v9A-SPO-DPO-Flash</p><p></p><h3 id="comradeshipxl-v9">comradeshipXL-v9</h3><p>It's a mix of ArtiWaifu, Animagine XL V3.1, and Pony. Haven't tested it, but I don't think LoRA will work.</p><p>comradeshipXL-v9T4 × 0.5 + comradeshipXL-v7A × 0.5 = comradeshipXL-v9</p><p></p><h3 id="comradeshipxl-v9t4">comradeshipXL-v9T4</h3><p>Comradeship XL Version 9 Test 4</p><p>Hassaku XL (Hentai) v 1.1 - Pony Diffusion V6 XL = marine-animeXL_h11pd6_locon</p><p>PD for Anime - Pony Diffusion V6 XL = marine-animeXL_pa2pd6_locon</p><p>autismmixSDXL autismmixConfett + marine-animeXL_pa2pd6_locon + marine-animeXL_h11pd6_locon = comradeshipXL-v8T1</p><p>ArtiWaifu Diffusion v1.0 unet × 0.7 + comradeshipXL-v8T1 unet × 0.3 + ArtiWaifu Diffusion v1.0 Text Encoder = comradeshipXL-v9T4</p><p></p><h3 id="comradeshipxl-v9t1">comradeshipXL-v9T1</h3><p>Comradeship XL Version 9 Test 1</p><p>ArtiWaifu Diffusion v1.0 unet × 0.7 + autismmixSDXL autismmixConfetti unet × 0.3 + ArtiWaifu Diffusion v1.0 Text Encoder = comradeshipXL-v9T1</p><p></p><h3 id="comradeshipxl-v7pp">comradeshipXL-v7PP</h3><p>This model is intended to combine the performance of pony_pencil-XL with support for Animagine XL V3.1 characters.</p><p>U-Net data from PD6 (Pony)-based models are merged. Therefore, some SDXL LoRAs may not work.</p><p>comradeshipXL-v7P unet × 0.5 + pony_pencil-XL v1.0.1 unet × 0.5 + comradeshipXL-v7P Text Encoder = comradeshipXL-v7PP</p><p></p><h3 id="comradeshipxl-v7a">comradeshipXL-v7A</h3><p>Pony Diffusion V6 XL - sd_xl_base_1.0 = marine-transXL-xl_to_pd6_locon</p><p>Animagine XL V3.1 - sd_xl_base_1.0 = marine-transXL-xl_to_am31_locon</p><p>comradeshipXL-v7P.json(Animagine XL V3.1, autismmixSDXL_autismmixConfetti, marine-transXL-xl_to_am31_locon, marine-transXL-xl_to_pd6_locon) = comradeshipXL-v7P</p><p>comradeshipXL-v7P unet × 0.7 + autismmixSDXL_autismmixConfetti unet × 0.3 + comradeshipXL-v7P Text Encoder = comradeshipXL-v7PT1</p><p>comradeshipXL-v7T5 unet × 0.55 + comradeshipXL-v7PT1 unet × 0.45 + comradeshipXL-v7T5 Text Encoder = comradeshipXL-v7PT2</p><p>comradeshipXL-v7PT2 + Kohaku-XL Epsilon Rev1 × comradeshipXL-v7A.json = comradeshipXL-v7A</p><p></p><h3 id="comradeshipxl-v7">comradeshipXL-v7</h3><p>Animagine XL V3.1 + Kohaku-XL Epsilon Rev1 * comradeshipXL-v7T5.json = comradeshipXL-v7T5</p><p>comradeshipXL-v7T5 + marine-animeXL_v06v02m * 0.5 = comradeshipXL-v7</p><p></p><h3 id="comradeshipxl-v6a">comradeshipXL-v6A</h3><p>Animagine XL V3.1 - Animagine XL V3.0 = marine-animeXL-3130</p><p>anima_pencil-XL v2.0.0 + marine-animeXL-3130 + marine-animeXL_v06v02m + (marine-animeXL-d1db × 0.6) = comradeshipXL-v6</p><p></p><h3 id="comradeshipxl-v6">comradeshipXL-v6</h3><p>Hassaku XL beta v0.6 - Hassaku XL beta 0.2M = marine-animeXL_v06v02m</p><p>Kohaku-XL Delta rev1 - Kohaku-XL Delta base = marine-animeXL-d1db</p><p>anima_pencil-XL v2.0.0 + (marine-animeXL-d1db × 0.65) + marine-animeXL_v06v02m = comradeshipXL-v6</p><p></p><h3 id="comradeshipxl-v5a-dpo">comradeshipXL-v5A-DPO</h3><p>Pony Diffusion V6 XL + dpo-sdxl-text2image-v1-LoRA + plastic-novel LoRA × 0.25 <em>+ </em>plastic-1 LoRA × 0.25 + plastic-2 LoRA × 0.25 <em>+ </em>plastic-3 LoRA × 0.25 = comradeshipXL-v5A-DPO</p><p></p><h3 id="comradeshipxl-v4bb-dpo">comradeshipXL-v4BB-DPO</h3><p><a target="_blank" rel="ugc" href="https://civarchive.com/models/264323?modelVersionId=298024">bulldozer_BETA</a> - Animagine XL V3 = marine-animeXL-am3_to_ab1 LoRA</p><p>Animagine XL V3 Base + dpo-sdxl-text2image-v1-LoRA + marine-animeXL-310001 LoRA + marine-animeXL-b7b5 LoRA + marine-animeXL-b71b5 LoRA + marine-animeXL-200121 LoRA + marine-animeXL-am3_to_ab1 LoRA = comradeshipXL-v4BB-DPO</p><p></p><h3 id="comradeshipxl-v5lite-dpo">comradeshipXL-v5Lite-DPO</h3><p>Simple LoRA merge model based on Pony Diffusion V6 XL.</p><p><a target="_blank" rel="ugc" href="https://civarchive.com/models/257749?modelVersionId=290640">Pony Diffusion V6 XL</a> + dpo-sdxl-text2image-v1-LoRA + <a target="_blank" rel="ugc" href="https://civarchive.com/models/264290?modelVersionId=298238">Smooth Anime Styles for Pony Diffusion V6 XL LoRA</a> + <a target="_blank" rel="ugc" href="https://civarchive.com/models/264290?modelVersionId=298005">Anime Styles for Pony Diffusion V6 XL LoRA </a>= comradeshipXL-v5Lite-DPO</p><p></p><h3 id="comradeshipxl-v4b-dpo">comradeshipXL-v4B-DPO</h3><p>Changed Animagine XL V3 to Animagine XL V3 Base</p><p></p><h3 id="comradeshipxl-v4-dpo">comradeshipXL-v4-DPO</h3><p>blue_pencil-XL v3.1.0 - blue_pencil-XL v0.0.1 = marine-animeXL-310001 LoRA</p><p><a target="_blank" rel="ugc" href="https://civarchive.com/models/260267/animagine-xl-v3?modelVersionId=293564">Animagine XL V3</a> + dpo-sdxl-text2image-v1-LoRA + marine-animeXL-310001 LoRA + marine-animeXL-b7b5 LoRA + marine-animeXL-b71b5 LoRA + marine-animeXL-200121 LoRA = comradeshipXL-v4-DPO</p><p></p><h3 id="comradeshipxl-v3c-dpo-310">comradeshipXL-v3C-DPO-310</h3><p>Changed blue_pencil-XL v2.9.0 to v3.1.0</p><p></p><h3 id="comradeshipxl-v3c-dpo">comradeshipXL-v3C-DPO</h3><p><a target="_blank" rel="ugc" href="https://civarchive.com/models/228270/anysomniumxl">AnySomniumXL</a> v2 - AnySomniumXL 1.2.1 = marine-animeXL-200121 LoRA</p><p><a target="_blank" rel="ugc" href="https://civarchive.com/models/247266/duchaiten-real3d-nsfw-xl">DucHaiten-Real3D-NSFW-XL</a> v1.0 - v0.16 = marine-beautyXL-100016 LoRA</p><p>Hassaku XL beta v 0.1 + dpo-sdxl-text2image-v1-LoRA + marine-animeXL-290001 LoRA + marine-beautyXL-100016 LoRA + marine-animeXL-b7b5 LoRA + marine-animeXL-b71b5 LoRA + marine-animeXL-200121 LoRA = comradeshipXL-v3C-DPO</p><p></p><h3 id="comradeshipxl-v3b-dpo">comradeshipXL-v3B-DPO</h3><p><a target="_blank" rel="ugc" href="https://civarchive.com/models/162577?modelVersionId=203416">Kohaku-XL beta7.1(?)</a> - Kohaku-XL beta5 = marine-animeXL-b71b5 LoRA</p><p><a target="_blank" rel="ugc" href="https://huggingface.co/bluepen5805/blue_pencil-XL/blob/main/blue_pencil-XL-v2.9.0.safetensors">blue_pencil-XL v2.9.0</a> - blue_pencil-XL v0.0.1 = marine-animeXL-290001 LoRA</p><p>Hassaku XL beta v 0.1 + dpo-sdxl-text2image-v1-LoRA + marine-animeXL-290001 LoRA + marine-animeXL-b7b5 LoRA + marine-animeXL-b71b5 LoRA = comradeshipXL-v3-DPO</p><p><a target="_blank" rel="ugc" href="https://civarchive.com/models/255395/baguette-anime-xl?modelVersionId=287909">Baguette-Anime XL v1.0 </a>- SDXL 1.0 = marine-transXL-xl_to_ba</p><p>comradeshipXL-v3-DPO + (marine-transXL-xl_to_ba * 0.6) = comradeshipXL-v3B-DPO</p><p></p><h3 id="comradeshipxl-v2-dpo-290">comradeshipXL-v2-DPO-290</h3><p><span style="color:rgb(193, 194, 197)">Changed blue_pencil-XL v2.0.0 to </span><a target="_blank" rel="ugc" href="https://huggingface.co/bluepen5805/blue_pencil-XL/blob/main/blue_pencil-XL-v2.9.0.safetensors"><span style="color:rgb(193, 194, 197)">v2.9.0</span></a></p><p></p><h3 id="comradeshipxl-v2-dpo">comradeshipXL-v2-DPO</h3><p><a target="_blank" rel="ugc" href="https://civarchive.com/models/162577?modelVersionId=192804">Kohaku-XL beta7</a> - <a target="_blank" rel="ugc" href="https://civarchive.com/models/162577?modelVersionId=183131">Kohaku-XL beta5</a> = marine-animeXL-b7b5 LoRA</p><p><a target="_blank" rel="ugc" href="https://civarchive.com/models/119012?modelVersionId=245614">blue_pencil-XL v2.0.0</a> - <a target="_blank" rel="ugc" href="https://civarchive.com/models/119012?modelVersionId=129169">blue_pencil-XL v0.0.1</a> = marine-animeXL-200001 LoRA</p><p><a target="_blank" rel="ugc" href="https://civarchive.com/models/140272?modelVersionId=251889">Hassaku XL beta v 0.1</a> + dpo-sdxl-text2image-v1-LoRA + marine-animeXL-200001 LoRA + marine-animeXL-b7b5 LoRA = comradeshipXL-v2-DPO</p><p></p><p>The license of comradeshipXL-v4/v6/v7 is the same as Animagine XL V3.</p><p>The license of comradeshipXL-v5 is the same as Pony Diffusion V6 XL.</p>

Comradeship XL (SDXL)

<p>This model is based on Illustrious-XL v0.1.<br /></p><p>Merge recipes can be found at this link.<br /><a target="_blank" rel="ugc" href="https://huggingface.co/hanzogak/comradeshipXL/tree/main/CSv14T1S-KIT">https://huggingface.co/hanzogak/comradeshipXL/tree/main/CSv14T1S-KIT</a></p>

comradeshipXL-v14T1S.safetensors

Comradeship XL

v14T1S

v14C

v14F

v14VWW

v14VW3H

v14VW3

v14KD2

v14VW2

v14KC

v14VX

v14K1AX

v14K1A

v17T4

v14K3

v14K

v17T3

v17T1

v14VT

v14V

v14T15V

v14T14

v14T14V3

v14T14V

v14T13B

v14T13A

v9MB4

v5AA

v9MB

v12T3-WDV01

v12T1-WDV01

v9AA-SPO-DPO-Flash-MaPOβ

v9A-SPO-DPO-Flash

v9T4

v9T1

v7PP

v5A-DPO

v4BB-DPO

v5Lite-DPO

v4B-DPO

v4-DPO

v3C-DPO-310

v3C-DPO

v3B-DPO

v2-DPO-290

v2-DPO

Just for testing purposes, for more info about the model: https://civitai.com/models/246299/comradeship-xl?modelVersionId=906471

comradeshipXL_v14t1s.safetensors

Files with SHA256: 89b13765e9616ba07a780c37effab29a878d7190eeec74e902908033ce8dd6f1