Skip to content
WorkflowListedExternal
Open source

Graizelle's Ultimate Lab - ComfyUI

❤️‍🔥 ⭐️ Graizelle's Ultimate Lab • Overview & Usage ⭐️ ❤️‍🔥

Sourcecivitai.com/models/1999539
TaskMultiCapabilitiesText to image · UpscalingFamilyIllustriousEstimated VRAMNot yet characterizedBgrade

Runtime profile

Access
External workflow
Status
Listed
Source
Civitai
Updated
Oct 24, 2026

Source description

❤️‍🔥 ⭐️ Graizelle's Ultimate Lab • Overview & Usage ⭐️ ❤️‍🔥

🖼 Prep & Size → 🔄 Load & Process → ✨ Detailing → 🚀 Upscale & Output

1️⃣ Image Sizing & Prep: 🖼 set dimensions & prepare inputs.

2️⃣ Load & Process: 🔄 img2img & optional LoRA.

3️⃣ Detailing: ✨ refine faces, hands, textures.

4️⃣ Upscale & Output: 🚀final resolution & save.

⚠️ DO NOT QUEUE FROM RUN BUTTON ⚠️

👉 always run from save image nodes.

🔀 Switches connect groups; Input 2 links to group on left.

✅ Provide valid inputs; missing images cause errors.

⚡ Groups can be run individually or in sequence.

What you need

Hardware and download-size estimates are not available yet.

Requirements

Models

5

  • 1x-ReFocus-Cleanly.pth

    Not resolved

    Upscaler · Unknown

  • 4x-UltraSharpV2.pth

    File unverified

    Upscaler · Unknown

  • bbox/hand_yolov8s.pt

    Not resolved

    Object Detector · Hugging Face · bbox/hand_yolov8s.pt

  • graizellesLustmix_v10.safetensors

    Not resolved

    Checkpoint · Unknown

  • segm/Anzhc_Face_seg_640_v3_y11n.pt

    Not resolved

    Vision model · Hugging Face · segm/Anzhc_Face_seg_640_v3_y11n.pt

Node packs

8

AI-generated commentary

AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.

Purpose

  • Graizelle's Ultimate Lab - ComfyUI is for preparing and processing images: set dimensions, optionally use img2img with a LoRA, refine faces, hands, and textures, then upscale and save at final resolution.

Flow

  • The stages are image sizing and prep, load and process, detailing, then upscale and output; switches connect groups that can run individually or in sequence.

  • Input 2 links to the group on the left.

Inputs and outputs

  • Provide a valid image and set its dimensions; img2img can optionally use a LoRA.

  • The final stage upscales and saves the image at final resolution.

Setup

  • The listing names Illustrious as the base model and provides no license information.

Dependencies

  • Named node packs include cg-use-everywhere, ComfyUI-YarvixPA, comfyui-utils-nodes, and comfyui-impact-pack.

  • Other named node packs are comfyui-impact-subpack, comfyui-mixlab-nodes, comfyui_essentials, and rgthree-comfy.

  • Named 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.

Configuration

  • To queue it, use a save image node rather than the Run button.

    Suggestion · not verified

Cautions

  • Provide a valid image; the listing says missing images cause errors.

    Suggestion · not verified

  • Before setup, check which ComfyUI package provides comfyui-mixlab-nodes and confirm the named model files are available in your environment.

    Suggestion · not verified

Does this need to be edited?

Sign in to send an edit request.

Sources

1 source
CivitaiPrimary
civitai.com/models/1999539

Verified Jul 19

Source excerpts

1 excerpt
NoteJul 19civitai.com/models/1999539

Source context: 187 downloads · Type Workflows · Base model Illustrious