CivArchive
    SexyShoes_Alche alchshoes – Women's Shoes, Heels & Fantasy Jeweled Footwear (Krea 2) - v1.0
    NSFW
    Preview 148058857
    Preview 148058958
    Preview 148058786
    Preview 148059044
    Preview 148058883
    Preview 148058991
    Preview 148059010
    Preview 148059038
    Preview 148059059
    Preview 148059072
    Preview 148059081
    Preview 148059119
    Preview 148059135
    Preview 148059154
    Preview 148059189
    Preview 148059214

    A LoRA for

    women's shoes and boots of every kind:

    pumps, sandals, mules, wedges, boots up to the thigh, and ornate jeweled / fantasy shoes. Use the trigger word alchshoes right before the shoe type.

    alchshoes — Women's Footwear LoRA for Krea 2

    A LoRA for women's shoes and boots of every kind: pumps, sandals, mules, wedges, boots up to the thigh, and ornate jeweled / fantasy shoes. Use the trigger word alchshoes right before the shoe type.

    What it does well

    • Realistic, well-shaped heels: stilettos, block heels, platforms, wedges.

    • Jeweled and fantasy shoes: crystals, chains, filigree, sculpted ornaments. This is where it shows its strongest effect over the base model.

    • Strappy and lace-up sandals, wedges, tall boots.

    • Glossy patent leather, satin, suede and metallic finishes.

    What it does NOT do (honest notes)

    • It is not a miracle. The base model already draws classic shoes well. This LoRA mainly pushes style and detail.

    • It leans toward sandals. The dataset contains many open-toe shoes. With closed classic shoes (closed mules, pumps, peep-toes) it may add straps or open the shoe up. For those, lower the strength to 0.4–0.5 or turn it off, and always write "closed toe" in the prompt.

    • Sometimes it makes feet too veiny or bony at high strength.

    • Small shoes in wide full-body shots get little detail. Use a legs shot when the shoe matters.

    • It does not reproduce specific brands or designer models.

    Usage

    Trigger and prompt structure. Follow the caption format the LoRA was trained on:

    a pair of [color] [material] alchshoes [shoe type] with [heel] and [toe/detail]
    

    Example:

    Full-body shot of a woman standing in a sunlit city street, navy knee-length dress, a pair of black patent leather alchshoes pointed pumps with stiletto heels, closed pointed toe, no straps
    

    Shoe types it was trained on. Write the class name right after alchshoes.

    • Pumps & mules: pointed pumps, peep-toe pumps, slingback pumps, mary jane shoes, heeled mules

    • Heeled sandals: ankle-strap heeled sandals, lace-up heeled sandals, thigh-high lace-up sandals, platform sandals, wedge sandals

    • Flats: flat sandals, slides, ballet flats, loafers, sneakers, espadrilles

    • Ornate: jeweled fantasy shoes

    • Boots: ankle boots, heeled knee-high boots, over-the-knee boots, thigh-high boots, lace-up heeled boots, lace-up combat boots, platform boots, sock boots, western boots, biker boots, riding boots, slouch boots, rain boots

    Recommended settings

    Strength0.8 (0.9–1.0 for jeweled/fantasy, 0.4–0.5 for closed classic shoes)FormatPortrait, about 1.5–2 MP (e.g. 1088×1936). Landscape tends to produce two women side by side. Very high resolutions (6 MP) create texture artifacts on the floor.Framing"Full-body shot" for the look; "Legs shot" or "Legs shot from the hips down" for shoe detail.

    Tips

    • Don't write "sexy": describe what makes the shoe sexy (very high stiletto heels, thin straps, glossy patent leather, platform sole).

    • For fantasy designs, use featuring and place the ornament on the shoe: "featuring a sculpted gold dragon coiling around the heel". This works much better than "with a dragon".

    • Use one theme per shoe.

    • For lace-only sandals, write made only of thin round cord laces … bare skin visible between every lace, otherwise the model adds wide bands.

    • For tall lace-ups and boots, add bare legs and a short dress or a high slit so the shoe isn't hidden.

    Training details

    • Base: Krea 2. Tested on a Krea 2 finetune, 12 steps.

    • Dataset: 405 real photos, no renders or illustrations.

      • The photos are mostly worn shoes, with some product shots.

      • Captions use a fixed class vocabulary.

    • Training: musubi-tuner, LoRA rank 32 / alpha 32, LR 1e-4, AdamW8bit, 3750 steps, resolution 768.

    • Released file: the final checkpoint. It was compared at a fixed seed against the 2000 / 2500 / 3000 / 3500 checkpoints and the no-LoRA output. The final had the cleanest shapes and feet.

    Feedback and example images are welcome, especially failures: they help the next version. 🙏

    Description

    First version experimental

    LORA
    Krea 2

    Details

    Downloads
    58
    Platform
    CivitAI
    Platform Status
    Available
    Created
    11/5/2026
    Updated
    11/6/2026
    Deleted
    -