CivArchive
    Artius 1-5 - v2.0-VAE
    NSFW
    Preview 5357654Preview 5357657Preview 5357666Preview 5357656Preview 5357658Preview 5357663Preview 5357659Preview 5357660Preview 5357665Preview 5357664Preview 5357667Preview 5357671

    Explore your imagination!
    Artuis is a versatile and flexible model, it allows you to generate crisp, high-resolution images:
    - Realistic portraits
    - NSFW
    - Stylized Art
    - Logos
    - Game assets
    - Texture
    - People, animals, food photos and more
    - Product concept
    - Any genre: Realistic, Fantasy, Sci-Fi, Cyberpunk, Anime and more

    This model is build with Noise Offset, so it tends to darker images, keep this in mind when making prompts

    This is SD 1.5 based model, also I have SD 2.1 based version: https://civarchive.com/models/27739/artius-v21

    This model is very NSFW sensitive, so be careful :-)

    If you liked my model, please leave a review, it helps other users to find this model and see its features!

    The model works best with the following samplers:
    Euler a
    DPM2
    DPM++ 2M Karras

    Optimal settings:
    Clip skip 1
    DPM++ 2M Karras
    25 Steps
    CFG Scale 5-6
    Resolution 512 or 768

    The model is prompt and NSFW sensitive, so it depends on your imagination.
    I've generated some demo images, you can study the prompt and make your own based on them.

    To make unique faces, mix faces that the model knows: [person1 : person2 : 0.5]

    Description

    Upgraded version of my model mix

    Checkpoint
    SD 1.5

    Details

    Downloads
    2,920
    Platform
    CivitAI
    Platform Status
    Available
    Created
    1/10/2024
    Updated
    9/27/2025
    Deleted
    -

    Files

    artius15_v20VAE.safetensors

    Mirrors

    Huggingface (1 mirrors)
    CivitAI (1 mirrors)