This is a LightWeight/Revisited variant of my workflow: SD3 / SDXL → SDXL / SD3.<a target="_new" rel="ugc" href="https://civarchive.com/models/511790/v135-workflow-sd3-sdxl-sdxl-sd3">Check it out here</a>.This workflow is designed to be both feature-rich and user-friendly. It includes:<ul><li>A global switch for SDXL/XLL, allowing you to configure everything with a single click.</li><li>On/Off switches for key functions to optimize rendering time.</li><li>Control panels for easy management, categorized for convenience.</li><li>Color-coded elements to guide the eye and renamed nodes for better clarity.</li><li>TextBoxs for Links if needed, Wildcards List, including my own Wildcards library and Luts collection</li></ul>The pipeline pathing is as follows:<ol><li>First Pass Diffusion</li><li>HiResFix / SUPIR / Both</li><li>Detailers Control Panel</li><li>Hands Refiner</li><li>Vagina Refiner</li><li>Face Detailer</li><li>Refine Anything (using words for detection)</li><li>Eye Detailer</li><li>Fine Details Upscale</li><li>Post-Process Control Panel</li><li>Upscale Control Panel</li><li>Save Image</li></ol>Each stage has its own On/Off switch to save rendering time.Specific prompts for Refiners.Face, and Eye Detailers share their own positive prompts.(Using a few related words for the area you are working on instead of the first pass diffusion prompt can make a significant difference.)Every step of the process includes a before-and-after comparison node at the bottom of the workflow.An Img2Img with autoprompt based on image input / Controlnet, among other cool things;)The default template comes with custom default settings, so you just have to download the nodes and models with ComfyUI Manager and you are ready to goEnjoy!<a target="_blank" rel="ugc" href="https://buymeacoffee.com/designedbycrt">https://buymeacoffee.com/designedbycrt</a>

(v1.45) SDXL/XLL WorkFlow

Files with SHA256: b569e56e69e869558538b431ab4f3c6de7ea2d073b8fa8094add80ee8bc139e1