CivArchive
    Not Artists Styles for SeaArt Furry XL 1.0 (Other Styles) EX 2.0 - Cosmic Void
    NSFW
    Preview 11683538
    Preview 11683549
    Preview 11683547

    These styles are similar to the Styles for Pony XL v6 2.0, but I can be a little different

    These LoRA will not work with Pony Diffusion V6 XL they are created for SeaArt Furry XL 1.0

    Styles won't work without Trigger Words!

    LoRA have been trained on the Pony Diffusion V6 XL and I do not guarantee out good quality on other Pony Models

    Preview generated without using ADetailer

    Recommended LoRA Strength: 0.5-0.7

    About Styles

    These styles are different because they are created by the Pony Diffusion V6 XL model itself, LoRA were trained on images created by Me using img2img and abstract textures and Some styles will be created by me without img2img or images created by Pony Diffusion V6 XL

    The OIS in the name stands for One Image Style, these models are literally trained on a single image

    About ALT (Alternative)

    These styles are already ALT, higher quality, more sharpness and fewer JPEG artifacts

    Blue Water, this style creates a watercolor effect with a slight cool effect

    Green Patina, this style creates a whiter textured watercolor effect with a slight bluish-greenish effect

    Cosmic Void, this style creates a dark and mysterious watercolor effect, and can create nighttime images

    Turquoise, this style creates a cool turquoise watercolor effect as if everything is underwater

    Pink Dreams, this style creates a soft pink hue on the image, the style is most similar to digital painting. The tokens pinkdreamsstyle, digital art, have less effect than concept art, realistic, but it is better to use these tokens together

    Red Lion, this style creates a very nice warm effect in the images and a slight watercolor effect and imperceptible paper texture effect

    Gold Fish, this style creates a vintage watercolor effect and a very strong paper texture effect

    Styles are based partially or entirely on images created by the Neural Network (Artificial Intelligence)

    Description

    Repeats: 20

    Epoch: 40

    Image Count: 4

    Network Rank (Dimension): 16

    Network Alpha: 8

    Batch size: 1

    Clip skip: 1

    Training steps: 3200

    Resolution: 1024x1024

    Train Resolution: 1024x1024

    LR Scheduler: cosine_with_restarts

    Optimizer: AdamW8bit

    Learning rate: 0,0005

    Text Encoder learning rate: 0,00005

    Unet learning rate: 0,0005

    Captioning: WD14 Captioning (SmilingWolf/wd-v1-4-moat-tagger-v2)

    Trigger Words: traditional media, realistic,

    Recommended LoRA Strength (Weight): 0.5-0.7

    FAQ

    Comments (4)

    PolygonMay 6, 2024
    CivitAI

    Did you do a hue/saturation shift on the dataset?

    obuyb404
    Author
    May 6, 2024

    No, I didn't change anything. the dataset is completely the same

    vatslokenMay 7, 2024
    CivitAI

    Thank you! ❤

    obuyb404
    Author
    Dec 4, 2024
    CivitAI

    I don't plan to update these styles anytime soon! (Maybe never even!)

    LORA
    SDXL 1.0

    Details

    Downloads
    107
    Platform
    CivitAI
    Platform Status
    Available
    Created
    5/6/2024
    Updated
    8/27/2026
    Deleted
    -
    Trigger Words:
    traditional media, realistic,

    Files

    Сosmic Void Style LoRA_SeaArt Furry XL 1.0.safetensors