CivArchive
    Virile Motion - v1.0
    NSFW
    Preview 1157615Preview 1157664Preview 1157619Preview 1157634Preview 1157637Preview 1157641Preview 1157644Preview 1157702Preview 1157709Preview 1157651

    If you'd like to buy me a beer or coffee! 🍺☕

    This model is my third merge and has been fine-tuned in order to produce convincing male-focused gens without the need for Loras, even with simple prompts.

    This model attempts to explore a more "animated" look in the style of Disney/Pixar movies.

    It is built upon my two previous merges, Virile Fusion and Virile Reality, however it is not a replacement and only aims at offering a different style, which could not be achieved by my two other models.

    In the end, whichever model you decide to use is a matter of preference.

    Models included in the merge are:

    Loras included in the merge are:

    While the model has been crafted to be male-centric, it also allows for the generation of other types of characters (including females) as well as landscapes, or objects.

    Recommended settings for good gens (Automatic1111):

    • Sampling Method: Euler A

    • Sampling Steps: 40

    • Hires. fix On

    • Upscaler: R-ESRGAN 4x+

    • Hires Steps: 20

    • Denoising Strength: 0.5

    • Upscale: 1.7/2.0

    • Width: 512

    • Height: 768

    • CFG Scale: 5

    I also highly recommend using After Detailer for faces, using the "mediapipe_face_mesh" model.

    VAE-wise, I would advise to use the following one: vae-ft-mse-840000-ema-pruned

    I would also like to mention and thank the Unstable Diffusion Discord Server's #men-only community who helped me learn a lot. Some of the gens done with the model include their prompts.

    Description

    Version 1.0

    • First version

    Checkpoint
    SD 1.5

    Details

    Downloads
    1,720
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    4/24/2025
    Updated
    5/6/2025
    Deleted
    4/24/2025

    Files

    virileMotion_v10.safetensors

    Mirrors

    Huggingface (1 mirrors)
    CivitAI (1 mirrors)