CivArchive
    Game-Icons.net Style - Simple Icons Style - v1.0
    Preview 23686444
    Preview 23686443
    Preview 23686466
    Preview 23686469
    Preview 23686468
    Preview 23686465
    Preview 23686467
    Preview 23686471
    Preview 23686470
    Preview 23686472
    Preview 23686473
    Preview 23686474
    Preview 23686475
    Preview 23686477
    Preview 23686478
    Preview 23686479
    Preview 23686476
    Preview 23686480
    Preview 23686481
    Preview 23686482

    This model creates simple artwork in the style of https://game-icons.net/

    Trained on 4131 icons from game-icons. CC BY 3.0 licence.

    Usage

    There is no trigger word with the model, but it's recommended to still describe the colors and icon style you want to use.

    Example prompt: Monochrome black frog princess icon<lora:G4m31c0n5:1>

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

    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.

    • You can try using locations only

    • Or using subjects, even characters doing specific things.

    • Indoor views are less trained, but you can get some cool effects sometimes

    • It doesn't always produce a round planet, but some other resulting views can be quite spectacular and unique anyway.

    Link to Training Data

    Like it?

    https://ko-fi.com/mnemic

    https://www.buymeacoffee.com/mnemic

    Description

    LORA
    SDXL 1.0

    Details

    Downloads
    526
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/10/2024
    Updated
    1/9/2026
    Deleted
    -

    Files

    Game-Icons Training Data v1.zip

    Mirrors

    G4m31c0n5.safetensors

    Mirrors

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