<h2 id="pixel-alchemy-30-7l5kzedgj">Pixel Alchemy 30</h2>Recommended settings :·         Sampler: dpmpp_2m_sde_gpu·         Scheduler : sgm_uniform·         CFG: 4·         Steps: 30 - 40<h2 id="pixel-alchemy-hyper-v20-and-v22-jh4gy9cwn">Pixel Alchemy Hyper V20 &amp; V22</h2>Improvement of human body and hands from the merger of the unreleased Pixel Alchemy V2.0 and Hyper-SDXL-12 steps CFG LoRASettings (ComfyUI) : Sampler : heunpp2, ddim, Euler/ Scheduler : sgm_uniform, ddim_uniform, simple / Steps : 16 to 20 / cfg : 2.5 to 3 For A1111, I won't be able to give any recommendations, because I don't use it, but I think that with a few tests you will end up finding what works best.<h2 id="pixel-alchemy-hyper-v16-9weiyko8f">Pixel Alchemy Hyper V16</h2>It's a merging of Pixel Alchemy V1.6 model with 2 LoRAs :<ul><li>Hyper-SDXL-12 steps CFG LoRA : <a target="_blank" rel="ugc" href="https://huggingface.co/ByteDance/Hyper-SD/blob/main/Hyper-SDXL-12steps-CFG-lora.safetensors">https://huggingface.co/ByteDance/Hyper-SD/blob/main/Hyper-SDXL-12steps-CFG-lora.safetensors</a></li></ul><ul><li>Hand Detail XL LoRA : <a target="_blank" rel="ugc" href="https://civarchive.com/models/260852/hand-detail-xl-lora">https://civarchive.com/models/260852/hand-detail-xl-lora</a></li></ul><h3 id="settings-(comfyui):-kq9i3yb3m">Settings (ComfyUI):</h3>Sampler : ddim / Scheduler : ddim_uniform / Steps : 20 / cfg : 3 Sampler : Euler / Scheduler : Simple / Steps : 14 / cfg : 2.5 Sampler : heunpp2/ Scheduler : sgm_uniform / Steps : 18 / cfg : 2.5but feel free to test others settings, specially for A1111<h2 id="pixel-alchemy-v16-szvm35jz0">Pixel Alchemy V16</h2>Version 1.6 of Pixel Alchemy brings a significant improvement in the rendering of photorealistic portraits, the texture of the skin appears more natural.It's a merging of Pixel Alchemy V1.3 with 1 checkpoint and 2 LoRAs<ul><li>RealVisXl model : <a target="_blank" rel="ugc" href="https://civarchive.com/models/139562?modelVersionId=344487">https://civarchive.com/models/139562?modelVersionId=344487</a></li><li>Steve McCurry - Photography SDXL LoRa : <a target="_blank" rel="ugc" href="https://civarchive.com/models/213283/steve-mccurry-photography-sdxl-lora?modelVersionId=240247">https://civarchive.com/models/213283/steve-mccurry-photography-sdxl-lora?modelVersionId=240247</a></li><li>Essenz - Better Photography (Style LoRa for SDXL 1.0) : <a target="_blank" rel="ugc" href="https://civarchive.com/models/198378?modelVersionId=250573">https://civarchive.com/models/198378?modelVersionId=250573</a></li></ul><h2 id="pixel-alchemy-v13-2xudz0wxk">Pixel Alchemy V13</h2>It's a merge of 4 checkpoints and 3 LORAs (see list below). One of the main goals is was to obtain a very versatile checkpoint. It's NSFW one.Quite efficient in rendering landscapes, realistic portraits, surrealism and gives better results with noise reinjection in ComfyUI (see below, the recommended extension)All my uploaded images were generated with low strength ADetailer (Eyes / hands / Face).<h3 id="models-merged-in:-7rd0jbegm">Models merged in:</h3><ul><li>Omnium : <a target="_blank" rel="ugc" href="https://civarchive.com/models/194245/omnium">https://civarchive.com/models/194245/omnium</a></li><li>Realism Engine SDXL : <a target="_blank" rel="ugc" href="https://civarchive.com/models/152525/realism-engine-sdxl">https://civarchive.com/models/152525/realism-engine-sdxl</a></li><li>Crystal Clear XL : <a target="_blank" rel="ugc" href="https://civarchive.com/models/122822/crystal-clear-xl">https://civarchive.com/models/122822/crystal-clear-xl</a></li><li>Juggernaut : <a target="_blank" rel="ugc" href="https://civarchive.com/models/133005?modelVersionId=348913">https://civarchive.com/models/133005?modelVersionId=348913</a></li></ul><h3 id="loras-merged-in:-e28mu2l19">LoRAs merged in:</h3><ul><li>Detail Tweaker XL : <a target="_blank" rel="ugc" href="https://civarchive.com/models/122359/detail-tweaker-xl">https://civarchive.com/models/122359/detail-tweaker-xl</a></li><li>xl more art-full / xl_real / Enhancer : <a target="_blank" rel="ugc" href="https://civarchive.com/models/124347/xlmoreart-full-xlreal-enhancer">https://civarchive.com/models/124347/xlmoreart-full-xlreal-enhancer</a></li><li> SDXL Film Photography Style : <a target="_blank" rel="ugc" href="https://civarchive.com/models/158945/sdxl-film-photography-style?modelVersionId=180569">https://civarchive.com/models/158945/sdxl-film-photography-style?modelVersionId=180569</a></li></ul><h3 id="recommended-settings-:-dxqa8itvp">Recommended settings :</h3>·         Sampler: dpmpp_2m / Euler / heunpp2 / dpmpp_3m_sde_gpu·         Scheduler : Karras / Exponentiel / sgm_uniform·         CFG: 5 - 7·         Steps: 36 - 46<h3 id="-bgjnw6yvw"></h3>

Pixel Alchemy

Pixel Alchemy Hyper V2.0 is a merge of Pixel Alchemy V2.0 (non published) with Hyper-SDXL-12 steps CFG LoRA. This version brings an improvement in anatomical renderings

Files with SHA256: 5ebbbbb77d6186279847100cc4e52ba1ec1de38a730e5d1573fdddfeb167669f