CivArchive
    Makina Mix - t3(ver-13)
    NSFW
    Preview 8844418
    Preview 8844423
    Preview 8844419
    Preview 8844429

    Photo realistic mix (majority Asian girls). To use with my loras.
    Recommended sampler Euler, 2M Karras, & Restart.

    v3.5: Cleaner background and model. Need new M35 specific Lora for best result.
    v2.4: Ease of use & realism somewhere in the middle. Better background and generic model.
    v2.2: Harder to use, more photographic look, less perfect, more realism.
    v1.4: Easier to use, more details. Recommended for beginners.

    More idols and newer version Loras also available at https://ko-fi.com/makina69


    Training Tips with v3.5
    30 images = 35 repeats.
    40 = 30 reps
    50 = 25 reps

    mixed_precision = "fp16"

    clip_skip = 2

    max_train_epochs = 6 (Epoch 4, 5 or 6 should be the best)

    [general_args.dataset_args]

    resolution = 768

    batch_size = 2

    [network_args.args]

    network_dim = 128

    network_alpha = 64.0

    min_timestep = 0

    max_timestep = 1000


    [optimizer_args.args]

    optimizer_type = "AdamW"

    lr_scheduler = "cosine"

    learning_rate = 0.0001

    unet_lr = 0.0001

    text_encoder_lr = 5e-5

    min_snr_gamma = 5

    Description

    About this version

    This is t3-13 version.

    I plan to focus on being active in the member channel for a while. It's difficult to make it while going back and forth to both places. I'll stop by from time to time~

    ★ The best-made model during production is only revealed to members who have sponsored through the sponsorship channel.

    Free members cannot receive the members-only model.

    Public paintings are available for viewing, so you can just look at them before leaving.

    (Free members cannot receive the members-only model.)

    https://www.patreon.com/t3278

    ★ We would appreciate it if you could upload at least one photo made using the t3 model posted on CIVITAI to the gallery.

    (I will try to refer to the prom and setting.)

    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

    t3-13 버전입니다.

    한동안은 집중해서 회원채널 에서 활동할 예정 입니다. 2곳 다 왔다 갔다 하면서 만들기 에는 힘드네요 간간히 들리겠습니다~

    ★ 제작 중 가장 잘 만들어진 모델은 후원 채널 에서 후원 해주신 회원분들께만 공개하고 있습니다.

    무료회원 분들은 회원전용 모델을 받으실 수 없습니다.

    공개 그림은 감상이 가능하니 그림만 구경 하시고 가셔도 됩니다.

    (무료회원 분들은 회원전용 모델을 받으실 수 없습니다.)

    https://www.patreon.com/t3278

    ★ CIVITAI에 올린 t3 공개한 모델을 사용해 만드신 사진을 1장 이상 갤러리에 올려주시면 감사하겠습니다.

    (프롬 및 세팅을 참고 하려고 합니다.)

    FAQ

    Checkpoint
    SD 1.5

    Details

    Downloads
    3,465
    Platform
    CivitAI
    Platform Status
    Available
    Created
    3/30/2024
    Updated
    4/30/2026
    Deleted
    -

    Files

    t3_Ver13.safetensors

    Mirrors

    CivitAI (1 mirrors)
    Other Platforms (TensorArt, SeaArt, etc.) (1 mirrors)

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.