CivArchive
    Jennifer - from IoM (Innocence or Money) game by MarcialART (Realistic) by X - v1.0
    NSFW
    Preview 147058823
    Preview 147058871
    Preview 147058879
    Preview 147058933
    Preview 147058983
    Preview 147059014
    Preview 147059043
    Preview 147059075
    Preview 147059110
    Preview 147059112

    MODEL IS PROVIDED AS-IS, I made this for myself but thought I should share :)

    NOT FOR COMMERCIAL USE: PERSONAL USE ONLY

    ======

    Jennifer from IoM (INNOCENCE OR MONEY), an interactive adult game.

    SUPPORT THE ORIGINAL CREATOR / CHECK OUT THE GAME

    DEVELOPER: MarcialART

    https://innocenceormoney.com/

    ======

    I wanted to convert a CGI character to realistic, and Jennifer seemed a perfect choice. She is a simple character with a unique look.

    I took 20 images, cropped them, then sized them to 816x1088. I used my img2img workflow for FLUX1-DEV and regenerated every image using FLUX. It took multiple attempts per image to get a consistent look. I used an NSFW capable illustrious model for the NSFW bits. Everything was touched up and worked on manually in photoshop until I had a clean 20 image dataset for training.

    The intent of this model is to use it for IMG2IMG. You can take the CGI version and using this LoRA turn it into a photorealistic image. You can also simply generate images... of course.

    See the sample images for prompts I used. It's nothing complicated, but I like how she turned out.

    ======

    LORA was trained in AI-TOOLKIT for the FLUX1-DEV model in 2250 steps using 20 images at 816x1088 resolution.

    Image generation was tested for 816x1088, 1024x1024 and 1440x816, it was acceptable for my purposes.

    ======

    WHAT THIS DOES WELL:

    I use my character LORAs for SFW generation, and for NSFW I use them to polish an image via img2img. I build my prompts to work in both the illustrious and the FLUX models that I use.

    WHAT THIS DOES NOT DO WELL:

    NSFW content. Nudity will still require another LORA, though I did use some NSFW images in training. (obviously try and see if you need an inpainting or img2img touchup)

    Description

    LORA was trained in AI-TOOLKIT for the FLUX1-DEV model in 2250 steps using 20 images at 816x1088 resolution.

    Image generation was tested for 816x1088, 1024x1024 and 1440x816, it was acceptable for my purposes.

    LORA
    Flux.1 D

    Details

    Downloads
    28
    Platform
    CivitAI
    Platform Status
    Available
    Created
    10/28/2026
    Updated
    11/4/2026
    Deleted
    -
    Trigger Words:
    jennifer

    Files

    jennifer_iom_flux.safetensors

    Mirrors