Graizelle's Ultimate Lab - ComfyUI

Graizelle's Ultimate Lab - ComfyUI takes prepared image inputs and dimensions, can process them with img2img and an optional LoRA, refines faces, hands, and textures, and outputs an upscaled image saved at final resolution.

The stages are image sizing and preparation, load and processing, detailing, then upscale and output.

Switches connect groups, Input 2 links to the group on the left, and groups can run individually or in sequence.

Provide a valid image input and set its dimensions; an optional LoRA can be used for img2img processing.

The output is a refined image saved at final resolution through save image nodes.

It is published by Graizelle, categorized as Workflows, and lists Illustrious as its base model.

The listed node packs are cg-use-everywhere, ComfyUI-YarvixPA, comfyui-utils-nodes, comfyui-impact-pack, comfyui-impact-subpack, comfyui-mixlab-nodes, comfyui_essentials, and rgthree-comfy.

The listed model files are 1x-ReFocus-Cleanly.pth, 4x-UltraSharpV2.pth, bbox/hand_yolov8s.pt, segm/Anzhc_Face_seg_640_v3_y11n.pt, and graizellesLustmix_v10.safetensors.

Queue the workflow from the save image nodes rather than the Run button.

Suggestion · not verified

For img2img processing, set dimensions and optionally add a LoRA.

Suggestion · not verified

Missing images cause errors, so provide valid image inputs.

Before using it, verify the exact package for comfyui-mixlab-nodes and confirm that all listed model files are available in your setup.

Suggestion · not verified