CivArchive
    Priya - v1.1
    NSFW
    Preview 145090523
    Preview 145090524
    Preview 145090529
    Preview 145090533

    Priya — a gorgeous young Indian woman with long dark black wavy hair, dark brown eyes, warm medium brown skin with natural texture, an oval face, fit athletic build, natural C cup breasts

    This LoRA captures Priya's face and identity for consistent renders across poses, outfits, and

    scenes. Retrained on the Krea 2 V30 base (RawRealDark_v2_V30) from a fresh 40-image identity set

    for sharper identity lock and natural skin texture.

    Trigger word: priya_face

    Recommended strength: 0.6 (0.4-0.8 range works; 0.6 is the sweet spot for face lock without

    identity bleed)

    Works best with: Krea 2 base models. Photorealistic style, natural lighting.

    Example prompt:

    priya_face, a gorgeous young Indian woman with long dark black wavy hair, dark brown eyes, warm medium brown skin with natural texture, an oval face, fit athletic build, natural C cup breasts, wearing a cream knit sweater, chest-up, warm smile, looking directly at

    the camera, soft natural window lighting

    Negative prompt tips: avoid "bright" before eye colour (it can cause glowing eyes).

    This is a fictional character. All images are AI-generated. A matched slim-body LoRA is available

    on this version for leaner silhouette shots.

    ⭐ If these Priya renders hit the way you hoped, a rating and a 👍 on the previews would help more

    than you'd think. Ten seconds, and it's the biggest boost an indie creator gets in search. Help

    her get noticed. 🙏

    ```

    ## Slim-body usage

    ```

    - Stack with the face LoRA: face @ 0.6 + slim body @ 0.8, same seed

    - Use on booty/back/side shots for a leaner, flat-rear look

    - Skip it on front-facing shots or if you want the curvy silhouette

    - Works best on Krea 2 bases

    ```

    ## Review

    ⭐ Enjoying Priya? A rating + 👍 on the previews makes a real difference to an indie creator. Shukriya!

    Description

    v1.1 — V30 retrain.

    What changed: retrained from scratch on the Krea 2 V30 base (RawRealDark_v2_V30) using a fresh

    40-image identity set for sharper identity lock and more natural skin texture. Replaces the

    blend-trained face LoRA.

    Training: 16 epochs / DIM32 alpha32 on RawRealDark_v2_V30 — 40 images -> 640 steps. Base: Krea 2.

    The companion body LoRA on this version is ALSO a fresh V30 retrain (DIM64 alpha64, on

    RawRealDark_v2_V30), uploaded as priya_slim_body_v2_v30.safetensors. It supersedes the previous body LoRA, which was

    trained on a different base than the images it was shown with.

    Same trigger word (priya_face) — drop-in replacement, no prompt changes needed.

    Recommended strength: 0.6.

    Gallery: 20 images rendered on the V30 base with both LoRAs above.

    FAQ

    Comments (2)

    aifinalOct 9, 2026
    CivitAI

    no picture of what you have made

    mad_macs
    Author
    Oct 9, 2026

    Weird, I know that Civit’s having issues displaying pics at times. Is it red with a question mark on it?