CivArchive
    Pareidolia Concept [Flux] :o) - v1.0
    Preview 27020684
    Preview 27020702
    Preview 27020712
    Preview 27020704
    Preview 27020713
    Preview 27020706
    Preview 27020708
    Preview 27020720
    Preview 27020715
    Preview 27020714
    Preview 27020718
    Preview 27020716
    Preview 27020710
    Preview 27020717
    Preview 27020711
    Preview 27020719
    Preview 27021713
    Preview 27021717
    Preview 27021716
    Preview 27021715

    This model lets you add faces to things.

    The model may produce slightly scary or cursed results sometimes, be warned!

    Usage

    Use the trigger word: "Pareidolia" along with the LoRA to activate it.

    Example prompt: Pareidolia a pizza that looks like a face <lora:PareidoliaFlux:1>

    I've found that most settings work well with this model. No special samplers or CFG-scale.

    The model may work without this prompting structure, but this is how it was trained and how I get good results.

    Note:

    I may be using the following extensions in the reference images: FreeU or ADetailer / Face Editor. I may also be using a specific Hires Checkpoint (swaps to another model when doing the hires steps). If your results don't match mine exactly, this may explain why.

    Tips and tricks

    Below are some tips and tricks for how to get even more out of the model.

    • Keep your prompt simple.

    • Add suffixes mentioning that you want something to look like something, see list below:

    ... that looks like a face
    a face made out of ....
    ... with a smiling face on it
    ... with a face on it

    Link to Training Data

    Like it?

    https://ko-fi.com/mnemic

    https://www.buymeacoffee.com/mnemic

    Description

    LORA
    Flux.1 D

    Details

    Downloads
    132
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/31/2024
    Updated
    1/9/2026
    Deleted
    -
    Trigger Words:
    pareidolia

    Files

    PareidoliaFlux.safetensors

    Mirrors

    CivitAI (1 mirrors)
    Other Platforms (TensorArt, SeaArt, etc.) (1 mirrors)