CivArchive
    Preview 49907572
    Preview 49907490
    Preview 49907494
    Preview 49907527
    Preview 49907499
    Preview 49907505
    Preview 49908221
    Preview 49908288
    Preview 49908585
    Preview 49908623
    Preview 49908676
    Preview 49908806
    Preview 49908824
    Preview 49908906
    Preview 49909013
    Preview 49909093

    《Film photography》

    This series of LoRA aims to restore various Asian photography styles. Through learning the style preferences in multiple details such as the color, focal length, and exposure of photography works, it can simulate the beautiful moments in the photographer's eyes relatively well, eliminate the problem of overly shiny skin in the FLUX model to the greatest extent, reduce the texture of artificial intelligence, and the output is closer to real photography.

    When using this series of Lora, it is recommended to start with a weight of 0.9. The following are the specific recommended parameters.

    Recommended weight: 0.9 - 1.5

    Recommended size: 768/1024/1536.

    Guidance condition: 2.0 - 3.0

    Steps: 20 - 40

    Sampler: euler/dpm++

    OK, that's all

    If you enjoy my work, please give me a "like" rating; it means a lot to me!If you enjoy my work, please give me a "like" rating; it means a lot to me!If you enjoy my work, please give me a "like" rating; it means a lot to me!

    Check out other creations here

    Thank you for reading up to here. English is not my native language. The above is translated by AI. If there is anything inappropriate, welcome to correct me. Thank you.

    I hope you have fun!Peace!

    Description

    Soft light

    Significantly enhance the light and shadow texture and texture details of F.1, bid farewell to the plastic feel.

    FAQ

    LORA
    Flux.1 D

    Details

    Downloads
    824
    Platform
    CivitAI
    Platform Status
    Available
    Created
    1/6/2025
    Updated
    4/28/2026
    Deleted
    -
    Trigger Words:
    SoftLight effect
    film grain

    Files

    Softlight.safetensors

    Mirrors

    Huggingface (1 mirrors)
    CivitAI (1 mirrors)

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.