CivArchive
    Featureless 2.5D Mix Pony - v2.0
    NSFW
    Preview 23664872Preview 23669709Preview 23670981Preview 23673348Preview 24281963Preview 24286158Preview 23983697Preview 23674876Preview 23683008Preview 23669742Preview 23983710Preview 23677640Preview 24764347Preview 24764358Preview 23677906Preview 23684728

    I don't speak English so I'm translating at ChatGPT. Let me know if the English is weird.

    I conducted training using images outputted by the Featureless 2.5D Mix from the SD1.5.
    V2 has a more 3D-like depiction than V1.

    SD1.5のFeatureless 2.5D Mixで出力した画像で学習を行いました。
    V2はV1よりもより3Dに近い描写となっています。

    Training Image Breakdown / 教師画像内訳

    I used the Pony Diffusion V6 XL as the pretrained model and conducted
    additional training with the following images.

    • Upper body images with various hair colors and hairstyles on a white background x 1000

    pretrained modelにPony Diffusion V6 XLを使用し、以下の画像を使い追加学習を実施しました。

    • 白背景の様々な髪色、髪形の上半身画像 x 1000

    Merging Method / マージ方法

    V1
     LoRA merge : Featureless Mix Pony V1 + trained LoRA(1.0)
     VAE : XL_VAE_C f0.51 has been merged

    V2
     LoRA merge : Featureless Mix Pony V2 + trained LoRA(1.0) = modelA
     Sum Merge : modelA + WAI-REAL_CN V8 (0.5)
     VAE : XL_VAE_C F1 and XL_VAE_C F0.51 at a ratio of 0.5

    License

    This model is merged with a model based on Pony Diffusion V6 XL and thus inherits
    the Fair AI Public License 1.0-SD. Additionally, unique restrictions on monetization
    have been added in Pony Diffusion V6 XL. For more details, please refer to the license
    section of Pony Diffusion V6 XL.

    このモデルはPony Diffusion V6 XLをベースとするモデルをマージしているため、
    Fair AI Public License 1.0-SDを継承しています。また、Pony Diffusion V6 XLにて
    マネタイズに関する独自の制約が追加されています。詳細はPony Diffusion V6 XL
    ライセンス項を参照ください。

    Description

    Checkpoint
    Pony

    Details

    Downloads
    974
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/10/2024
    Updated
    9/30/2025
    Deleted
    -

    Files

    featureless25DMix_v20.safetensors

    Mirrors

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