<h3 id="notice:-if-you-encounter-an-error-for-the-sam-model-download-the-sam-model-i-have-provided-and-place-it-in-the-sams-folder-under-the-model-directory-in-your-comfy-install.-rpvi2k8v9">Notice: If you encounter an error for the SAM model; download the SAM model I have provided and place it in the SAMS folder under the Model Directory in your comfy install. </h3><h2 id="lowvram-compatible-workflow-(remastered)-equ1ot4jo">LowVRAM Compatible Workflow (Remastered)</h2>This is a workflow intended for LowVRAM Users like myself, but can be used with Higher VRAM Cards as well.SPECIAL THANKS TO : @Jadewind for helping me identify issues with the last version that I missed! Killer job friend!<ul><li>Tested on a 3050Ti 4GB Mobile GPU</li><li>Tested on all SDXL Resolutions</li><li>Pre-Configured</li><li>Download links included for Detailer and Upscaler Models</li><li>Built in OoM (Out of Memory) "Buffers" for convenient restart points.</li><li>Full ADetailer type Pipeline</li><li>Dual Upscalers (CR and Latent)</li><li>Includes "Anything Everywhere" Nodes for a clean UI experience (No Spaghetti)</li><li>Efficiency Nodes for reduced node clutter</li><li>Group Notes for explanation and configuration purposes.</li></ul>

DogFace's SDXL Workflow - LowVRAM Compatible

This version fixes a number of issues associated with the workflow that I overlooked before release.<ul><li>CR Upscale Buffer was not connected to the Latent Upscale Nodes and was passing straight to Save Node. (Fixed)</li><li>Incorrect Link for one or more Detailer Models (Fixed)</li><li>Included directions for placing Detailer models (added)</li><li>Double checked workflow for additional issues that may have been missed (Verified)</li></ul>If you encounter any issues with the updated workflow please contact me directly via Chat or leave a comment on the page.Thank you and enjoy!

Files with SHA256: 0ade401621692808a9270503f7b14d3703b2ca4801f2b4630e3b288aea6a791c