CivArchive
    Emma Watson - Flux - v1.1
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined

    I trained this lora on 25 images of Emma Watson for 1600 steps, enjoy :D

    v1.2 improved quality, no trigger required. This is the same model I posted on huggingface a few days ago.

    v1.1 updated the model to require the trigger emmwat, after training extensively on triggers, using the person's name reduces model accuracy. please let me know if you prefer the model trigger or not. thanks ^^

    v1.0 does not require a trigger word

    Below is my flux LORA training guide:
    https://civarchive.com/articles/6678

    Description

    FAQ

    Comments (17)

    JaneBAug 21, 2024· 1 reaction
    CivitAI

    Do you think using her name reduced the accuracy because it already existed in some (probably intentionally mutilated) form in the model or just because it associated with a regular person. Like if you made an unknown persons the trigger would it work like the made up trigger word.

    119123Aug 21, 2024· 3 reactions

    yes i do, if you generate images of Emma Watson with out the lora it always generates a girl with similar features to her but does not look like her. this bleeds in with the lora and reduces the likeness of the model.

    JaneBAug 21, 2024

    @punzel Interesting, had a feeling it was happening with some of my loras. Time to name a few celebs as john smith.

    JaneBAug 21, 2024· 1 reaction

    @punzel By the way have you tried the civitai trainer? Your guide is fantastic and gave me great results but civit is about half the price plus you can generate buzz from your work to even lower that.

    119123Aug 21, 2024

    @JaneB ooo ill have to check that out!! thanks!

    JaneBAug 21, 2024

    @punzel Please report back, I trust your opinion more than I trust mine :)

    119123Aug 21, 2024

    @JaneB i will! :3

    barlogspam176Aug 22, 2024
    CivitAI

    Thanks for improving. DO you believe if the person is not very famous adding her real name would affect the LoRA performance?


    PS we are rediscovering things from the SDXL loRA

    Use alphanumerical triggernames, use 2000 steps, etc.

    119123Aug 22, 2024

    hii! if the trigger generates a similar person each time, it may affect the model; if it's random, it shouldn't.

    irixAug 22, 2024· 2 reactions
    CivitAI

    This lora is almost perfect, great job!

    HikariasAug 22, 2024
    CivitAI

    amazing job, What settings did you use in the last version?

    119123Aug 22, 2024

    hii, thank you!! the guide linked in the description has all the settings i used!

    MyjhgtuhgfgAug 22, 2024· 1 reaction
    CivitAI

    Very nice 👍🙂

    MyjhgtuhgfgAug 22, 2024· 1 reaction
    CivitAI

    So good

    HikariasAug 24, 2024
    CivitAI

    Hello another question, In the workflow it says unet, What exactly model are you using? Could you share the model?

    psychonaut69Sep 4, 2024

    @punzel where is the "Workflow" your talking about? Cant find it..

    LORA
    Flux.1 D

    Details

    Downloads
    1,285
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    8/22/2024
    Updated
    5/17/2026
    Deleted
    5/23/2025
    Trigger Words:
    emmwat

    Files

    flux_emmwat.safetensors

    Mirrors

    CivitAI (1 mirrors)
    TensorFiles (1 mirrors)