CivArchive
    Anima Compact Controlnet + Facedetailer Workflow - v1.0
    NSFW
    Preview 135059577
    Preview 135059590
    Preview 135060122

    V3 Update :

    • Added a FaceDetailer node. It detects, re-renders, and re-attaches faces to the generated image, resulting in sharper and more detailed faces overall.

    • You can Increase bbox_threshold and drop_size to reduce detection of small/background faces.

    • All detectors and the SAM model come with the node once you install it from the ComfyUI Library, so you won't need any external resources.

    V2 Update :

    Since the Anima ControlNet node was recently updated, the older version will no longer work if you update your ComfyUI.

    So, I had to update this workflow to make it compatible with the latest version.

    ControlNet has added a new "Model Patch" input. I've added the required node, but you will need to download the necessary models and place them in your:

    ComfyUI/models/model_patches/

    Download them from here:
    https://huggingface.co/Comfy-Org/Anima-LLLite/tree/main/model_patches

    Additional Improvements

    • Added a Size Selector to easily switch between popular image sizes and flip the dimensions.

    • Added an Image Comparer (On top the Save Image node)

    • Added a Stack LoRA Loader.

    • Moved a few things around to make the workflow more compact and easier on the eyes.

    If You don't need the controlnet just select the yellow nodes and press Ctrl+B to bypass them , then it would be a simple Text to Image workflow.


    A small, clean, and lazy-friendly Anima workflow for those who don't want to play "Where is that damn node?" every time they want to change something.

    I made this workflow to keep the important stuff close together:
    ✅ Easy checkpoint switching
    ✅ Quick character/model changes
    ✅ Simple prompt editing
    ✅ Fast sampler and generation setting adjustments
    ✅ Less scrolling, less node hunting, more creating

    The idea is simple: everything you actually touch while experimenting is right in front of you. No giant spaghetti workflow with 500 nodes

    Just open it, pick your model, change your character/prompt, tweak your settings, and generate.

    Required Model:

    You need to download the Anima ControlNet-LLLite model first and place it this path:

    ComfyUI/models/controlnet

    Download:
    https://huggingface.co/kohya-ss/Anima-LLLite/tree/main

    This workflow uses the Anima LLLite ControlNet setup, so make sure the model is installed before running it.

    Quick heads-up: CivitAI did that funny thing before where my other workflow straight-up disappeared into the void. 💀
    I’ve uploaded it again, but if this happened to this one once more , just grab one of the images, they contain the workflow.

    Have fun creating!

    Description

    FAQ

    Comments (2)

    ExzDreamAug 9, 2026
    CivitAI

    Why do I need to upload an image? I just want to generate a picture from a text description. I’ve only been using Comfy for six months, so please excuse me if this seems like a silly question.

    NeuralVandal
    Author
    Aug 10, 2026· 1 reaction

    Hi , uploading an image into this workflow Provides it with a depth map to follow and draw your idea based on it , for example if you are having a trouble generating a gymnastic pose , selfie composition , objects location and etc in your image , You can generate an image using a stronger tool like GPT image or draw a basic depht map version of the idea then feed it to the controlnet node.

    Ultimately If you don't need it You can select all the yellow nodes then press Ctrl+B (or right click on them select bypass) to bypass them.

    Workflows
    Anima

    Details

    Downloads
    391
    Platform
    CivitAI
    Platform Status
    Available
    Created
    6/27/2026
    Updated
    8/20/2026
    Deleted
    -

    Files

    animaCompactControlnet_v10.json

    Mirrors