CivArchive
    Deep Breast Sucking (NoobAI V-Pred 1.0 + Pony + SD 1.5) - v2.0
    NSFW
    Preview 3724608
    Preview 3724645
    Preview 3724609
    Preview 3724615
    Preview 3724616
    Preview 3724643
    Preview 3724642
    Preview 3724648
    Preview 3724639
    Preview 3724625
    Preview 3724644
    Preview 3724641
    Preview 3724657
    Preview 3724633
    Preview 3724614
    Preview 3724668
    Preview 3750101
    Preview 3750102
    Preview 3750103
    Preview 3750105

    Deep Breast Sucking v1 (NoobAI V-Pred 1.0)

    This is an experimental model. It makes good pictures but not every time. If you like it, please follow me.

    Base Model: NoobAI V-Pred 1.0

    Weight: 1

    Starter Prompts:

    DBS, 1girl, 1boy, huge breasts, faceless male, breast sucking, masterpiece, best quality, newest

    DBS, 2girls, huge breasts, breast sucking, masterpiece, best quality, newest

    Look at my pictures for ideas and NoobAI page for model prompt guide. The character, and style, can change how good the picture is, so experiment.

    Deep Breast Sucking v1 (Pony)

    This is an experimental model. It makes good pictures but not every time. If you like it, please follow me.

    Base Model: AutismMix Confetti

    Weight: 1

    Starter Prompt: score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, BREAK source_anime, rating_explicit, 1girl, 1boy, huge breasts, nipples, breast sucking, DBS, <lora:DBSPDv1:1>

    Negative: breast grab

    Look at my pictures for ideas. The base model, character, and style, can change how good the picture is.

    Deep Breast Sucking v2 (1.5)

    This model is the result of countless days of work. If you like, please post your results and a review!

    Weight: 1

    Starter Prompt: <lora:DBSv2:1> 1girl, 1boy, hetero, huge breasts, nude, nipples, simple background

    You can add more too. Look at training tags in Lora metadata to get ideas. This model does not work good with yuri but if you're patient it is possible. I will add more yuri in v3.

    Dimensions: 768x768, 512x768, 768x512

    Each dimension setting works different, try them all out. Some gives certain positions more, some works better with other Loras.

    This model works well with characters that don't have a strong style or pollution. It also works good with many styles.

    Training Info

    Trained on 113 hand picked pictures manually edited and cropped to reduce pollution. Trained on NAI for 4850 steps, this amount was chosen by evaluating models 50 steps at a time up to 6000 steps. Clip skip 2, x768.

    Description

    Increased training data over double and fine tuned for several days

    FAQ

    LORA
    SD 1.5
    by FWS

    Details

    Downloads
    3,168
    Platform
    CivitAI
    Platform Status
    Available
    Created
    11/18/2023
    Updated
    4/22/2026
    Deleted
    -

    Files

    DBSv2.safetensors

    Mirrors

    Huggingface (1 mirrors)
    CivitAI (1 mirrors)