CivArchive
    Kio Style - [NoobAI/Anima] - V2 (NoobAI Colab)
    NSFW
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined

    V1 (Anima):

    19-image Lora that allows you to generate images in the art style of Kio. I made this Lora because it was thanks to this artist that first introduced me to Sonic's R34 art and I created this Lora as a form of homage. Model created in Google Colab.

    prompts: @kio \(artist\)

    negative prompts: artist name, jpeg artifacts, low res, signature, text, score_1, score_2, score_3,

    Base model: anima-base-v1.0

    Repeats: 4

    Steps: 912

    Epochs: 24

    Unet LR: 1e-4

    Text Encoder LR: 0.0

    LR Scheduler: cosine_with_restarts

    LR Scheduler Number: 1

    Min-SNR Gamma: 5

    Network Dim: 16

    Network Alpha: 16

    Train Batch Size: 2

    Optimizer: AdamW8bit

    V2:

    19-image Lora that allows you to generate images in the art style of Kio. I made this Lora because it was thanks to this artist that first introduced me to Sonic's R34 art and I created this Lora as a form of homage. Model created in Google Colab.

    prompts: by kio \(artist\)

    negative prompts: artist name, signature, jpeg artifacts

    Base model: NoobAI Eps 1.1

    Repeats: 5

    Steps: 360

    Epochs: 20

    Unet LR: 1e-4

    Text Encoder LR: 1e-5

    LR Scheduler: constant

    LR Scheduler Number: 1

    LR Warmup Ratio: 0.01

    Min-SNR Gamma: 6

    Network Dim: 32

    Network Alpha: 32

    Train Batch Size: 6

    Optimizer: AdamW8bit

    V1:

    19-image Lora that allows you to generate images in the art style of Kio. I made this Lora because it was thanks to this artist that first introduced me to Sonic's R34 art and I created this Lora as a form of homage. Model created in Google Colab.

    prompts: by kio \(artist\)

    negative prompts: artist name, signature, jpeg artifacts

    Base model: NoobAI Eps 1.1

    Repeats: 2

    Steps: 760

    Epochs: 20

    Unet LR: 1e-4

    Text Encoder LR: 1e-5

    LR Scheduler: constant

    LR Scheduler Number: 1

    LR Warmup Ratio: 0.01

    Min-SNR Gamma: 6

    Network Dim: 32

    Network Alpha: 32

    Train Batch Size: 1

    Optimizer: AdamW8bit

    Description

    The number of Repeats was changed to 5, Steps was reduced to 360, and Batch Size was increased to 6.

    FAQ

    LORA
    NoobAI

    Details

    Downloads
    49
    Platform
    CivitAI
    Platform Status
    Available
    Created
    2/4/2026
    Updated
    8/22/2026
    Deleted
    -
    Trigger Words:
    by kio \(artist\)

    Files

    Kio Style.zip

    Mirrors

    CivitAI (2 mirrors)

    Kio_Style_V2.safetensors

    Mirrors

    CivitAI (1 mirrors)