CivArchive
    DMMID Style - LORA Version
    Preview 209930Preview 209929Preview 209928Preview 209927Preview 209926Preview 209925Preview 209924Preview 209923Preview 209922

    Making models is time consuming. Do you like what I do? Feel free to buy me a coffee

    This is my new amazing hires sized Model based on Jim Poisons Amazing Dataset! If you want your own style/person trained, just DM me with a dataset of ~20 imgs on discord Flonix#4022 and ill train it for you!

    trained on high res images

    DO NOT USE A NEGATIVE PROMPT FOR MAXIMUM STYLE

    set the weight lower than 1 to get it to follow your prompt more.

    Use with SD upscale on 0.3 denoise and Swin IR4x

    Example Prompt, made with Additional Networks:

    Award-winning digital painting, (close up:1.2) - the (Fantastic landscape of Mars:1.1), cinematic art, hdr, gloomy atmosphere, (by dan mumford style:1.1), (by dmmid style:1.1), by giger, by lovecraft
    Negative prompt: bad, errors, bad anatomy, ugly face, fog, (matte colors:1.2)
    Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 8, Seed: 887100127, Size: 768x768, Model hash: 7bde1c2752, ENSD: 31337

    Description

    Look at the other uplaoded versions on my profile aswell.

    This is only extracted. so it isnt as good as the trained one imop

    Checkpoint
    SD 1.5

    Details

    Downloads
    202
    Platform
    CivitAI
    Platform Status
    Available
    Created
    3/7/2023
    Updated
    9/27/2025
    Deleted
    -
    Trigger Words:
    dmmid style

    Files

    dmmidStyle_loraVersion.safetensors

    Mirrors