CivArchive
    Preview 95567027Preview 95567768Preview 95567503Preview 95567508Preview 95567530Preview 95567663Preview 95567601Preview 95567822Preview 95567595Preview 95567653Preview 95567722

    This is a place for experimenting with SD1.5 LoRA.

    The main goal is overall enhancement rather than focusing on a single concept.

    Dora_nsfw_remember is intended to complement my test merge model, but since the training is done on NovelAI v1, they should work fine with its derivative models.

    my test model: https://civarchive.com/models/1246353/sd15modellab

    nai_v2_highres is a high-resolution stabilizing DoRA for novelai_v2.

    Please download the official checkpoint from the URL below.

    I’ve also made a safetensors version just in case.

    https://huggingface.co/NovelAI/nai-anime-v2

    https://civarchive.com/models/1772131

    nai_v2_semi-real is a semi-realistic style DoRA for novelai_v2.

    ■I use OneTrainer for training and ComfyUI for inference.

    ■I will share my training settings and inference workflow as much as possible.

    ■If the prompt is short, the background may become simple or the style may lean toward realism.
    By using the uploaded tipo_workflow, you can automatically generate longer prompts—so please give it a try!

    ■Sometimes saturation occurs due to overfitting and the model’s compatibility. Adjusting DoRA , prompt weight strength, or reviewing the cfg can help improve this.

    ■There’s also a high-resolution inference workflow using kohya_deep_shrink.

    It expands composition and removes the need for high_res_fix.

    1152px offers a good balance of quality, stability, and speed, while 1536px is more dynamic and detailed.

    By the way, this Dora was created to give SD1.5 a level of concept understanding comparable to my PixArt-Sigma anime fine-tune.

    SD1.5 with Dora applied will likely be the most compatible refiner—it's ideal for i2i tasks.

    my pixart-sigma finetune.

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

    Description

    It’s closer to a realistic style now, but it isn’t fully photorealistic.

    The training used real photos, but it doesn't enforce full realism.

    While that may seem like a downside, it avoids forgetting unrealistic concepts, maintaining flexible generation.

    At weight 1, the realism is strong. Around 0.75 gives more stable, semi-realistic results with fewer artifacts.

    It also learned the “realistic” tag, which helps bring out the realistic style.

    I don’t use this DoRA alone.

    Instead, I usually merge it with models like novelai_v2_highres to balance anime aesthetics with subtle realism for a more convincing output.

    DoRA
    SD 1.5
    by hjhf

    Details

    Downloads
    22
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/21/2025
    Updated
    9/30/2025
    Deleted
    -
    Trigger Words:
    realistic

    Files

    sd15LoraLab_naiV2SemiRealV02.safetensors