<h1 id="welcome-to-realizum-xl-2l11h4w99">Welcome to Realizum XL</h1><hr /><h3 id="this-model-delivers-decent-photorealistic-capabilities-truly-shining-in-close-up-images.-you-can-expect-highly-realistic-and-detailed-results-when-generating-visuals-that-zoom-in-on-subjects.-it's-a-solid-option-for-producing-clear-and-well-defined-close-up-shots.-built-on-the-sdxl-model-it-also-offers-various-capabilities-for-animated-and-cgi-based-generation-though-its-primary-focus-remains-on-realism.-i0vvglbxi">This model delivers decent photorealistic capabilities, truly shining in close-up images. You can expect highly realistic and detailed results when generating visuals that zoom in on subjects. It's a solid option for producing clear and well-defined close-up shots. Built on the SDXL model, it also offers various capabilities for animated and CGI-based generation, though its primary focus remains on realism.</h3><h3 id="this-model-excels-at-intimate-close-up-shots-across-diverse-subjects-like-people-races-species-and-even-machines.-it's-highly-versatile-with-prompting-allowing-for-both-sfw-and-decent-nsfw-outputs.-hk82q5tu6">This model excels at intimate close-up shots across diverse subjects like people, races, species, and even machines. It's highly versatile with prompting, allowing for both SFW and decent NSFW outputs.</h3>&lt;Copy the node workflow from the demo images to get my exact workflow and defined values.&gt;<h2 id="tensorart-link-8i5t9x104"><a target="_blank" rel="ugc" href="https://tensor.art/models/880632198342922466/Realizum-XL-V2-Halo">TensorArt Link</a></h2><h3 id="how-to-use-ik0klz7fe">How to use?</h3>Prompt: Simple explanation of the image, try to specify your prompts simply. Steps: 10 CFG Scale: 1.8Personal settings. Portrait: (Steps: 10 + CFG Scale: 1.8), Details: (Steps: 20 + CFG Scale: 3) Sampler: DPMPP_SDE +Karras Hires fix with another sampler for fixing irregularities<a target="_blank" rel="ugc" href="https://github.com/nicofdga/DZ-FaceDetailer">Face Detailer</a> recommended if image is not a closeup portrait.Vae baked inNegative prompts example template:Start with no negative prompts, and add whatever is not needed in negative or add the below for consistent<pre><code>bad proportions, low resolution, bad, ugly, bad hands, bad teeth, terrible, painting, 3d, render, comic, anime, manga, unrealistic, flat, watermark, signature, worst quality, low quality</code></pre>Image size:<pre><code>Use any SDXL portrait or landscape resolutions. Or use the SDXL Empty Latent Image (rgthree)</code></pre><h1 id="&quot;update-v2&quot;-xeoogp150">"UPDATE V2"</h1><h2 id="v2-&quot;halo&quot;-z6wylohds">V2 "Halo"</h2><ul><li>Improvements have been made.</li><li>Prompts are followed more accurately.</li><li>More realistic faces .</li><li>Improvements on whole image, structures, poses, scenarios.</li><li>NSFW quality improved.</li></ul>How to use?Prompt: Simple explanation of the image, try to specify your prompts simply.Steps: 8 - 20CFG: 1.5 - 3Personal settings. Portrait: (Steps: 8 + CFG Scale: 1.5), Details: (Steps: 10 + CFG Scale: 2)Sampler: DPMPP_SDE +Karras Hires fix with another sampler for fixing irregularities.<a target="_blank" rel="ugc" href="https://github.com/nicofdga/DZ-FaceDetailer">Face Detailer</a> recommended if image is not a closeup portrait.Vae baked in ~Note this is my first time working with image generation models, kindly share your thoughts and go nuts with the generation~

Files with SHA256: 91b6cdee5731738f3fbea236fd8bb87c71fc420a142bd1829802a9fe73269c3f