CivArchive
    [FLUX|PONY] Emma Watson - DoRA v1.0
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined

    FLUX: My take with another technique on Emma Watson with FLUX.

    Can probably lower the weight a bit to like 0.8

    Prompt her with just "woman" or "Jenny".

    Enjoy!


    My take on the FooBar of generative AI: Emma Watson

    Hope you enjoy :)

    Description

    FAQ

    Comments (12)

    handyman1986Jul 23, 2024
    CivitAI

    Correction, all of your newest DoRAs have the "LoRA" label in the "type" category.

    CrunchyBanana
    Author
    Jul 23, 2024

    Wait, there is a DoRA category? I'm gonna change that. Thank you!

    handyman1986Jul 23, 2024· 1 reaction

    @CrunchyBanana Yup, there is! No problem! 👍

    HikariasJul 24, 2024
    CivitAI

    Hello, I'm curious abot which model are you using for tranining, Your lora's look amazing.

    CrunchyBanana
    Author
    Jul 24, 2024

    I'm using the same train of thought I used with my SD1.5 Loras:

    Train on the model, that probably most models have merged into them. In my case: Ponyrealism

    CrunchyBanana
    Author
    Jul 24, 2024

    but to clarify a bit further:

    It's not the model that determines the quality that much. Sometimes I make some small merges of different models for fun and training.

    99% of the quality is to spend some time with the source images. I'd say about 50% of the time for my Loras I spend on preparing the dataset. The results are always nearly the same, no matter the model or optimizer you use.

    HikariasJul 24, 2024

    @CrunchyBanana Thank you, For me training pony realism (any model) It's becoming a pain in the ass. For some reasonn Euler A it's the sampler tha works better for my loras. But Euler A looks soft and not sharp.

    CrunchyBanana
    Author
    Jul 24, 2024

    @Hikarias ye Euler is kinda smoothing everything. DPM++ and Restart are nice with realistic Pony. Also Karras and Align your Steps as Scheduler work well.

    HikariasJul 24, 2024

    @CrunchyBanana Yeah I know, But for some reason DPM++ Karras, It's not working well with my lora's I'm not sure why, I have tried using onetrainer and kohya with not good results. Using prodigy optimizer and cosine or constant. 16 rank 16 alpha.

    CrunchyBanana
    Author
    Jul 24, 2024

    @Hikarias Use Prodigy with cosine. iirc it doesn't adapt when set on constant. But whatever you pick: Make sure your source data is excellent :)

    Try Restart/Automatic as Sampler. Its slow, but kinda foolproof once you found a fitting cfg

    HikariasJul 24, 2024

    @CrunchyBanana Yeah I was using Prodigy with cosine, 1 LR, But with the same problem, Probably it's something else. Anyway thanks for your advices! I don't want to waste more your time :)

    CrunchyBanana
    Author
    Jul 24, 2024

    @Hikarias no problem. Shoot me a message if you have further questions. I'll try to help if I can :)

    LORA
    Pony

    Details

    Downloads
    1,274
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    7/23/2024
    Updated
    5/6/2026
    Deleted
    5/23/2025
    Trigger Words:
    ohwx
    1girl

    Files

    CrunchyBanana_PONY_DORA_Emma_Watson.safetensors