CivArchive
    Preview 96443475Preview 96443551Preview 96443479Preview 96443521Preview 96443485Preview 96443731Preview 96443740Preview 96444114Preview 96443812Preview 96443548Preview 96443763Preview 96443680Preview 96443802Preview 96443854Preview 96443893Preview 96443894Preview 96443911Preview 96443914Preview 96444087Preview 96448385

    This is my experiment in creating an SD1.5 merge style model for i2i.I am satisfied with the current state, but I will update it if I feel anything is needed.or I might share ways to enhance this model rather than updating it directly.

    ■Since the model now has both anime and real versions, the detailed explanations have been moved to each model’s tab.

    Both are merged models created by selecting multiple high-quality models with minimal artifacts.

    ■With the three models—asian, real, and anime—now available, it could be fun to adjust their mix to find your ideal style.

    ●asian 0.5 + real 0.5 might yield a more mixed, half-and-half look.

    ●asian 0.5 + anime 0.5 might produce a cute, 2.5D-style appearance.

    Feel free to experiment with different ratios.

    ■Since this is just a merge, it shares a common SD1.5 limitation where NSFW tags may not be fully understood or followed.

    I have decided to manage the concept-enhancing LoRA separately.

    https://civarchive.com/models/1253884/sd15loralab

    Of course, it can be used on its own, It is designed for i2i processing the models below.

    https://civarchive.com/models/505948/pixart-sigma-1024px512px-animetune

    ■Depending on the situation, this extension may also improve colors and contrast.

    https://github.com/Haoming02/sd-webui-diffusion-cg

    https://github.com/Haoming02/comfyui-diffusion-cg

    ■Using external tools for level adjustment is also a good option.

    Reducing gamma slightly while enhancing whites can improve contrast even further.

    Using these should help achieve color rendering closer to that of SDXL.

    ■Surprisingly, generating at 768px or 1024px sometimes works fine.If you want more stability, merging with Sotemix could help.But since most LoRAs are trained at 512px, high resolutions can break the output.So it’s safer to use highres.fix or kohya_deep_shrink when using LoRAs.

    Personally, I prefer i2i upscaling over highres.fix, as it tends to produce fewer artifacts.

    Description

    This is a merged model tuned to generate the common “cute Asian-looking woman” style.

    I merged about 20 models that are good at producing Asian-looking outputs. If you use the asian tag, you’ll almost certainly get an Asian appearance.

    You can still generate images without the asian tag, but the chance of an Asian look is lower. That’s true for most models—without the tag, you won’t consistently get Asian-looking results.

    For what it’s worth, my real_v001 merge also produces Asian looks just fine if you include the asian tag.

    As a differentiator, this model tends to produce cuter faces, while real_v001 often leans toward a broader, pan-continental facial impression.

    If you mix asian 0.5 + real 0.5, you may get a more mixed facial look. Feel free to experiment.

    Checkpoint
    SD 1.5
    by hjhf

    Details

    Downloads
    391
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/25/2025
    Updated
    10/1/2025
    Deleted
    -
    Trigger Words:
    realistic, asian

    Files

    sd15ModelLab_asianV001.safetensors

    Mirrors