CivArchive
    [Workflow] AingMixKrea + FaceDetailer (t2i) - v1.0
    NSFW
    Preview 147197828
    Preview 147197829

    [Workflow] AingMixKrea + FaceDetailer

    [1] What this workflow does

    Stage 1 (Base generation) : Generates the image with AingMixKrea

    Stage 2 (Face refinement) : FaceDetailer detects the face and redraws it

    [2] Requirements

    - Latest version of ComfyUI

    - Tested and working on 8GB VRAM (RTX 4060 Ti); more VRAM is better.

    - 32GB+ system RAM recommended.

    [3] Required custom nodes

    ComfyUI Impact Pack

    ComfyUI Impact Subpack

    rgthree-comfy

    ControlAltAI Nodes

    Comfyui_LG_Tools

    gguf (calcuis)

    [4] Required model files and where to put them

    ◆ Stage 1: Base generation (Krea2)

    ComfyUI\models\diffusion_models\KREA2\AingMixKrea-int8_convrot.safetensors (~13.5GB)

    - https://civarchive.com/models/3012914/aingmix-krea2-kroma-pussy-loras

    ComfyUI\models\text_encoders\Huihui-Qwen3-VL-4B-Instruct-abliterated.safetensors (~8.9GB)

    - https://huggingface.co/ahmed22xa/Huihui-Qwen3-VL-4B-Instruct-abliterated-comfy

    ComfyUI\models\vae\qwen_image_vae.safetensors (~254MB)

    - https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/vae

    ◆ Stage 2: Face detailer (Z-Image Turbo)

    ComfyUI\models\diffusion_models\moodyRealMix_zitV7.safetensors (~12.3GB)

    - https://civarchive.com/models/621441/moody-real-mix?modelVersionId=3005060

    ComfyUI\models\text_encoders\qwen_3_4b.safetensors (~8GB)

    - https://huggingface.co/Comfy-Org/z_image_turbo/tree/main/split_files/text_encoders

    ComfyUI\models\vae\ae-zit.safetensors (~335MB)

    - https://huggingface.co/Comfy-Org/z_image_turbo/tree/main/split_files/vae

    ComfyUI\models\loras\ai-friend.safetensors

    - https://civarchive.com/models/2996379/a-ing-korean-cute-girl

    ◆ Face detection (Impact Pack)

    ComfyUI\models\ultralytics\bbox\face_yolov8m.pt

    - https://huggingface.co/Bingsu/adetailer/tree/main

    ComfyUI\models\sams\sam_vit_b_01ec64.pth

    - https://huggingface.co/datasets/Gourieff/ReActor/blob/main/models/sams/sam_vit_b_01ec64.pth

    [5] How to use

    1. Drag json onto the ComfyUI canvas to load it

    2. install the custom nodes in [3] and restart

    3. Check that each loader node has the correct model selected

    4. Type prompt

    5. Pick the aspect ratio / megapixels in the "resolution" node

    6. Have fun

    Description

    Workflows
    Krea 2

    Details

    Downloads
    16
    Platform
    CivitAI
    Platform Status
    Available
    Created
    10/29/2026
    Updated
    10/31/2026
    Deleted
    -

    Files

    WorkflowAingmixkrea_v10.json

    Mirrors

    CivitAI (1 mirrors)