CivArchive
    Anime-Luna | Glazed Porcelain & Cobalt Style (Flux.3 Klein 9B) - v1.0
    NSFW
    Preview 149782683
    Preview 149783005
    Preview 149782953
    Preview 149782968
    Preview 149783174
    Preview 149783185
    Preview 149783931
    Preview 149792207
    Preview 149798504

    Unlike workflows that require layering multiple separate adapters (such as those inspired by "kintsugi" or ceramic art), this model delivers a cohesive aesthetic "out of the box": glossy, glazed porcelain-like skin, a delicate crackle texture, radiant golden eyes, and elegant floral patterns in cobalt blue and gold. Because the clothing and background were clearly separated from the character during the captioning process, Luna is not tied to any specific outfit or pose she adapts seamlessly to any wardrobe, lighting, or environment.

    Usage and Trigger

    Trigger word: r64f3animeluna

    LoRA Strength: 0.85 – 1.0 (works perfectly at 1.0 without causing overtraining artifacts)

    Recommended Generation Settings

    Base model: Flux.3 Klein 9B Base

    Steps: 55 – 65 65 is optimal)

    CFG Scale: 3.5

    Sampler: UniPC

    Scheduler: SGM Uniform sgm_uniform)

    Weight Guide & Reference Mode

    0.85 – 1.0 (Full Porcelain & Character Mode):

    Generates the full glazed ceramic shader, cobalt accents, and original persona aesthetic from scratch.

    0.15 (Real Person / Reference Restyle): Because the model is very densely trained, set the LoRA weight to 0.15 when editing or restyling real human portraits from image references.

    At 0.15, it preserves the person's real facial likeness and proportions while applying a clean, high-gloss anime finish without texture distortion.

    Training Details

    Dataset: Custom synthetic dataset at 1024x1024 resolution

    Configuration: Rank 64 | 2000 steps | Learning Rate (LR): 2e-4

    Training Process: The model was trained using my own high-speed fork of the AI-Toolkit. Links, intermediate checkpoints, and training files

    Training toolkit (GitHub):

    OrakulStudio/AI-Toolkit-Windows11

    https://github.com/OrakulStudio/AI-Toolkit-Windows11

    Telegram channel:

    https://t.me/Orakul_Studio

    Subscribe to be the first to receive new models, intermediate checkpoints (at the 1000 and 1500 step marks), and full optimizer state files optimizer.pt). These will be useful if you decide to further fine-tune the model or apply this "porcelain shader" effect to your own dataset.

    Description

    LORA
    Flux.3 Klein-base

    Details

    Downloads
    14
    Platform
    CivitAI
    Platform Status
    Available
    Created
    11/21/2026
    Updated
    11/22/2026
    Deleted
    -
    Trigger Words:
    r64f3animeluna

    Files

    VikingHF-v1.1.0.zip

    Size:
    2.59 KB
    SHA256:

    Mirrors

    r64f3animeluna.safetensors

    Mirrors

    CivitAI (1 mirrors)

    flux3-klein-top-structured-node-image-edit-2image-reference.zip

    Size:
    7.73 KB
    SHA256:

    Mirrors