CivArchive
    Portrait_Homa_LoRA_v1 - Homa V1
    Preview 68581259
    Preview 68581273
    Preview 68581260

    This is a LoRA trained on photos of a real person for facial reconstruction and portrait generation.
    Best used for close-up portraits and natural lighting.
    Trained using the DAdapt method with face-focused prompts.
    Recommended weight: 0.6–0.8.
    Ideal for general female character generation with realism.

    This model is based on a real person. Do not use for impersonation or deepfakes of others.

    Description

    LORA
    Flux.1 D

    Details

    Downloads
    81
    Platform
    CivitAI
    Platform Status
    Available
    Created
    4/7/2025
    Updated
    4/28/2026
    Deleted
    -

    Files

    Homa.safetensors

    Mirrors

    CivitAI (1 mirrors)