CivArchive
    Essenz - Darkest Dungeon [Chris Bourassa] (Style LoRa for SDXL 1.0) - v1.2 [FINAL]
    NSFW
    Preview 3582034
    Preview 3582037
    Preview 3582035
    Preview 3582036
    Preview 3582033
    Preview 3582041
    Preview 3582038
    Preview 3582039
    Preview 3582042
    Preview 3582040
    Preview 3582043
    Preview 3582046
    Preview 3582044
    Preview 3582048
    Preview 3582045
    Preview 3582047
    Preview 3582049
    Preview 3582050


    Disclaimer

    Financial support is very much appreciated, but please do so by donating to my Ko-Fi instead of sending me Buzz, as I currently have no uses for CivitAI Buzz!


    Description

    An SDXL 1.0 LoRa made by AI_Characters for producing images with an artstyle similar to the game Darkest Dungeon - with the art mainly created by Chris Bourassa.


    Recommended generation parameters

    Weight: 1.0 (adjust down as needed when used in conjunction with other LoRa's)

    Model: SDXL 1.0 with 0.9 vae

    Steps/Sampler/CFG/Resolution: 25 steps | DPM++ 2M Karras | CFG 7 | 1536x1536

    'Kohya Deep Shrink' settings: 4 blocks | 2 downscale | 0 start | 0.35 end | skip = true

    Positive prompt: high-definition 8k

    Negative prompt: text, blur, low-resolution, low-quality, grainy, glossy, poorly drawn, amateur, poorly shot, compression artifacts

    'CLIPTextEncodeSDXL' ComfyUI node resolution: 4096x4096


    Trigger words (must be included in the prompt for the LoRa to take effect!)

    • 'comicish artwork in dgst artstyle'


    Further usage notes

    • It doesn't replicate the style perfectly as unfortunately it does not produce the typical black/not visible eyes as seen in-game. I tried a few different things to no avail.


    Usage permissions

    You may not sell this model, merges containing it, or images generated with it.

    Credit me when using this model in a merge or hosting it on a generation service.


    TL:DR Training Workflow

    1. Train full finetune with a dataset of 20-100 images using this config on a Vast.AI rented A100 80gb GPU

    2. Extract LoRa at 512/512 dimensions using these settings

    3. Resize LoRa to 16 ranks using these settings


    Changelog

    v1.2 [FINAL]

    • complete rework; higher epoch count, trained with EMA, reworked captions, reworked dataset preparation, small trigger words change - overall much better likeness and quality at the cost of some slight bias and overtraining increase - final version for now

    v1.1

    • retrained with new captions: slightly better style likeness, slightly better flexibility, less bias towards the subject matter of the training data; added "comic book" to the trigger word

    v1.0

    • Initial release


    Description

    FAQ

    LORA
    SDXL 1.0

    Details

    Downloads
    1,399
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    4/24/2025
    Updated
    5/1/2026
    Deleted
    4/24/2025
    Trigger Words:
    comicish artwork in dgst artstyle

    Files