CivArchive
    Caligula NG - v1.0
    NSFW
    Preview 105403204
    Preview 105403206
    Preview 105404140
    Preview 105404142
    Preview 105404143
    Preview 105404141
    Preview 105404399
    Preview 105404398
    Preview 105404402
    Preview 105404775
    Preview 105404776
    Preview 105404774
    Preview 105405036
    Preview 105405038
    Preview 105405250
    Preview 105405253
    Preview 105405254
    Preview 105405251
    Preview 105405530
    Preview 105405531

    After using the excellent Gonzales NSFW pony and MoP models together in different passages to generate my images, I decided to combine them into a single model.

    I consider this model to have good NSFW capabilities, also performing well with SFW content. It responds satisfactorily to prompts, including natural language prompts. It has issues with multiple characters in a scene, requiring more generations for a good result.

    It's a DMD model that requires few generations and offers a good cost-benefit ratio between speed and quality. My recommendations for this model are the LCM sampler and exponential, karras, or beta schedulers. 8 to 12 steps already guarantee good generation quality.

    Consider using it as a refiner for a Flux model; it greatly improves realism.

    Also try the fantastic Gonzales NSFW pony and MoP models.

    Description

    FAQ

    Comments (9)

    whambamthankuOct 18, 2025· 2 reactions
    CivitAI

    Fantastic model! I was wondering how you created those videos? I thought this was only for image generation?

    thewizardofoz
    Author
    Oct 18, 2025· 2 reactions

    Thank you friend, I use the model to generate only the images that I use to generate the videos with wan 2.2 i2v, I intend to post the workflow that I use to generate the videos soon, as soon as I have time to organize it

    whambamthankuOct 21, 2025

    @thewizardofoz Awesome, thanks for the advice! Can't wait to read your workflow!

    mqblbhaiOct 24, 2025· 2 reactions
    CivitAI

    Huge fan of your work! Keep up the good work

    thewizardofoz
    Author
    Oct 24, 2025

    Thanks brother, if you use the model, be sure to post it here so I can see the result.

    INFRASIGNALNov 26, 2025· 1 reaction
    CivitAI

    This model has been a joy to work with, though I do struggle to prevent website watermarks. I've tried increasing CFG and adding negative prompts like (((website commercial))) as well as trying "no-text" in positive with mixed results. Switching between Beta Karras and Exponential schedulers while keeping the same seed also helps eliminate text watermarks sometimes. Open to other suggestions.

    thewizardofoz
    Author
    Nov 29, 2025· 1 reaction

    This is the Achilles' heel of this model; problems in the training are proven. Since it's a DMD2 model, the negative prompt isn't listened to very often, so I end up removing the text in post-production.

    Jess_PlayinJan 15, 2026· 2 reactions
    CivitAI

    This has gone straight to No. 1 in my favorite Checkpoints list. Well done, and thank you!

    hkg364Jan 23, 2026
    CivitAI

    I like it so far. Good checkpoint

    Checkpoint
    SDXL 1.0

    Details

    Downloads
    718
    Platform
    CivitAI
    Platform Status
    Available
    Created
    10/11/2025
    Updated
    5/12/2026
    Deleted
    -

    Files

    caligulaNG_v10.safetensors

    Mirrors

    CivitAI (1 mirrors)

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.