CivArchive
    Preview 138933142

    Simple Krea2 Dataset Creator

    LC123 Nodes: https://github.com/lonecatone23/ComfyUI_LC123_nodes

    You will need to update. I just uploaded them to ComfyUi. If you get errors, pull them from the repo


    Instagram: https://www.instagram.com/synth.studio.models/

    Buy me a☕ https://ko-fi.com/lonecatone

    This represents many hours of work that I give away for free. If you enjoy it, Please make sure to 👍like and post to my workflows. That is how you support me. Also, feel free to ⚡tip 😉


    There's nothing better out there for making character datasets.

    V8.0

    While messing with my flagship Krea workflow, I realized that Remove Backgroud helps Identity edit.

    • Added remove background

    • added preview windows to verify

    • changed the prompt selector📝 switch to prompt list names instead of numbers for ease of use

    • ⚠️ you will need to update the LC123 nodes. If you have an error, that is because ComfyUi is slow in updating. Pull the pack directly from the Repo

    V7.0

    • Removed the anchor prompt from the final Text output

      • Thanks @artyclaw for pointing it out 👍

    • minor start setting tweak

    V6.0 Pro Grade

    V5.0 (because I can't ever stop messing with stuff 🤔)

    • Got irritated with the standard Image compare node taking the comparison numbers and spreading them out across the top of the screen, making them useless, so made my own.

    • Added a quality modifier and clothes swap anchor⚓ to make it so you can drop any image in and get different clothing, plus better skin.

    • Redid the prompts to add colors to every piece of clothing 👗👚. Huge difference in outfit variation now.

    • Updated the notes to include all the changes.

    • Added a link to my nodes (which should be in the manager).

      • I also added the folder in the .zip file

    V4.1

    • rebuilt the filename node so that the number aligns with the name of the image without having to change it.

    • renames teh Power LoRA loader to add "Character" to it.

    • Moved the "play sound 🔊" to the end of the workflow.

    V4.0

    • Added newer version of ID Edit LoRA

      • added link to the Repo

    • Added 🎨 Post processing Suite

      • Contrast adaptive sharpen

      • Color Match to Image 🖼️

      • Image adjust

    • Added a better aspect ratio control

    • updated notes

    V3.1: addresses the ComfyUi list selector bug.

    I take a lot of time to get these to work. If there are issues, please let me know so that I can correct them.

    Description

    V4.0

    • Added newer version of ID Edit LoRA

      • added link to the Repo

    • Added Post processing Suite

      • Contrast adaptive sharpen

      • Color Match to Image 🖼️

      • Image adjust

    • Added a better aspect ratio control

    • updated notes

    FAQ

    Comments (8)

    12756499Aug 7, 2026
    CivitAI

    Where are those Image Filter Adjustments options you mention in the note? I don't think there's an “Edge Enhance” or “Detail Enhance” option there.

    I really like this dataset workflow, it turns out to be super useful👍

    lonecatone23
    Author
    Aug 7, 2026

    ????

    The adaptive sharpen, color match, and image filter nodes at the end.

    12756499Aug 7, 2026

    I can't paste an image here, so let me quote verbatim what's written in the “🎨 Post-processing Notes/ 说明” section:

    "Image Filter adjustments: Pretty self explanatory.

    Bright center is 0.

    Contrast and saturation center are 1.

    I use sharpness here. 0.5-1

    Blur: (no, just no)

    Edge enhance: 0-1.

    Detail enhance: true"

    lonecatone23
    Author
    Aug 7, 2026

    @Acalyphoideae Ahhh. I complied that from another set of notes. Looks like I may not have deleted enough of the notes below.

    I'll look at it and adjust tonight

    12756499Aug 8, 2026

    That's fine, thanks for the explanation👍

    lonecatone23
    Author
    Aug 8, 2026

    @Acalyphoideae already fixed.

    tokazouAug 8, 2026
    CivitAI

    Thanks to this workflow, I managed to train my first OC LoRA. I also found an issue with ComfyUI Image Saver. It seems to be hard-coded to not number the first output image. As a result, every image-caption pair generated by this workflow is off by 1. I asked my AI agent to fix it, and it patched the custom node after 2 failed attempts to patch the workflow. Here's the fix: https://github.com/Tokazou/ComfyUI-Image-Saver/commit/7a691a9b4a0aa6ba20ca68b9f69524e2cba64822. If you're happy with the code changes, click the 3-dots menu -> View file -> Download raw file, and copy it to your ComfyUI/custom_nodes/comfyui-image-saver directory. P.S. This is a drunk comment 🍻

    lonecatone23
    Author
    Aug 8, 2026· 1 reaction

    You can literally just group rename them 🤔.

    I may make a custom node at some point

    Workflows
    Krea 2

    Details

    Downloads
    481
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/6/2026
    Updated
    9/4/2026
    Deleted
    -

    Files

    krea2IDEditCharacterDataset_v40PostProcessing.json

    krea2IDEditProGrade_v4001PostProcessing.zip

    krea2IDEditCharacterDataset_v40PostProcessing.zip