CivArchive
    Lily-Rose Depp (FLUX + SDXL) - SDXL v1.0
    Preview undefinedPreview undefinedPreview undefinedPreview undefinedPreview undefinedPreview undefinedPreview undefinedPreview undefinedPreview undefinedPreview undefined

    Please Donate Buzz for FLUX Lora Training !

    FLUX v1.0 :

    Trained on FLUX dev with 96 photos of Lily-Rose Depp with detailed GPT-4 captions. Tested on FLUX 1.dev (full) and FLUX fp8 and FLUX nf4 ! Use around strength 0.8-1.2. No keywords needed! Distilled CFG around 1-4 and CFG 1.0 (without negative prompt). Clipskip 1. Can be used for example as follows:

    Positive : {Artstyle, Character and scene description in usual FLUX fashion}, <lora:Lilly_Rose_Depp_FLUX_v1-000040:1>

    SDXL v1.0

    Lora trained on 200 HQ photos of actress and model Lily-Rose Depp. Lora strength between 0.8-1.2 for most use cases.

    Description

    LORA
    SDXL 1.0

    Details

    Downloads
    418
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    2/14/2024
    Updated
    7/7/2025
    Deleted
    5/23/2025

    Files

    lirosedepp_xl_1_standard_merger_31_78_05_05.safetensors