CivArchive
    All Disney Princess XL LoRA Model from Ralph Breaks the Internet - v2.0
    NSFW
    Preview 4058459
    Preview 4058460
    Preview 4058461
    Preview 4058462
    Preview 4058465
    Preview 4058464
    Preview 4058466
    Preview 4058479
    Preview 4058480
    Preview 4058490
    Preview 4058491
    Preview 4058495
    Preview 4058494
    Preview 4058496
    Preview 4058506
    Preview 4058507
    Preview 4058508
    Preview 4058505
    Preview 4058617

    All Disney Princess XL LoRA Model - Ralph Breaks the Internet

    If You Like This Model, Give It a ❤️

    This LoRA model is trained on screen capture images featuring beloved Disney princesses from the movie Ralph Breaks the Internet, including Rapunzel, Snow White, Ariel, Aurora, Belle, Cinderella, Elsa, Anna, Jasmine, Mulan, Merida, Tiana, Moana, and Pocahontas. It's designed to be an All-in-One Model for your creative endeavors.

    Check out SD1.5 Version Here: https://civarchive.com/models/202866/all-princesses-from-disneys-ralph-2-ralph-breaks-the-internet-or-all-in-one-lora-model

    Bonus Characters

    Additionally, this model includes representations of other characters like Vanellope, Shank, Raya, Namaari, Asha, and Rapunzel with short hair. While these extras are included, the quality may vary.

    Quick Tips

    • Direct Name Usage: You can generate any princess by directly prompting their names, such as Anna, Ariel, Aurora, Belle, Cinderella, Elsa, Asha, Jasmine, Merida, Moana, Mulan, Namaari, Pocahontas, Rapunzel, Raya, Shank, Snow White, Tiana, Vanellope.

      • More Character in v2 including: Alice, Chel,Esmerada, Jane Porter, Kida, Megera,Mirabel Madrigal, Isabela Madrigal, Dolores Madrigal and some secret character!

    • LoRA Scale: Optimal LoRA scales range between 0.6-0.7 for close-up character generation and 0.3-0.5 for full-body generation. Combining these scales using the ADetailer plugin can yield enhanced results. Ensure an adequate number of sampling steps for better output.

    • Base Models: Although various base models can function, models with animation styles like DreamShaper or RealCartoon are preferred for optimal performance.

    Enjoy exploring the LoRA!

    Description

    This version add more data. The high resolution images are created by using v1.0 LoRA and img2img upscaling.
    I also add more character in to this model as well.

    FAQ

    Comments (32)

    marusameDec 12, 2023· 13 reactions
    CivitAI

    I find this funny and I know its splitting hairs but elsa is actually not a disney princess, she is a Queen, one of the only good queens that I know of in disney movies. Anna is the princess.

    tylrzzz192Jan 7, 2024· 5 reactions

    Shes a princess at the start of the movie

    marusameJan 7, 2024

    @tylrzzz192 ahh right its been awhile forgot about that

    wikka9220386Jun 1, 2024

    no longer a princess, I am afraid

    Zane410Dec 13, 2023
    CivitAI

    Hey i know this is kinda dumb to ask but im new to diffusion, how do i install this since its LX cuz im getting. "Error: Could not load the lora model! Reason: Sorry, could not load E:\Diffusion\models\lora\princess_xl_v2.safetensors. You're trying to use a SDXL LoRA model with a SD1 Stable Diffusion model. They're not compatible, please use a compatible model!" or should i just use a diff one?

    JeoniDec 13, 2023· 1 reaction

    For this lora you need an SDXL checkpoint. You are using an SD1 checkpoint which is not compatible. However, the author also did a similar lora for SD1, you can see it here on "suggested resources".

    titansteng
    Author
    Dec 13, 2023

    @Jeoni Yes, Thank You.
    Check out this model: https://civitai.com/models/202866

    Zane410Dec 13, 2023

    so could i also just get a SDXL checkpoint? and it would work?

    titansteng
    Author
    Dec 14, 2023

    @Zane410 Correct. If you don't have any machine problem to run XL in the first place, that would also work.

    ishadowxDec 26, 2023· 1 reaction
    CivitAI

    Why is Jazmin the only one who doesn't look like Jazmin at all in both SD1.5 and SDXL? Is this from a specific Disney Channel Jazmin?

    titansteng
    Author
    Dec 26, 2023· 1 reaction

    I agree that Jasmine doesn't resemble the Jasmine from the Aladdin animation. I believe this might be due to excessive redesigning of the original Jasmine 3D model from 'Ralph Breaks the Internet'. I'm considering addressing this point if I can find some time.

    coudysJan 5, 2024· 1 reaction
    CivitAI

    are the training data no longer available? It keeps saying server error :(

    3275099Feb 2, 2024· 3 reactions
    CivitAI

    anyone else get issue with this lora generating cross-eyed people? I noticed even the sample images have it.

    titansteng
    Author
    Feb 2, 2024

    Have you try ADetailer or Face detailer?

    smaftApr 27, 2024

    stop using ahegao lol :D just kidding.

    randba1974557Jul 25, 2024

    that's pretty accurate with the style. disney/pixar make characters look beautiful or cute by having them at resting 10% ahegao face pretty much.

    LayzeeApr 1, 2024
    CivitAI

    Do I also have to download the training data for this to work? Or can I just download the lora?

    titansteng
    Author
    Apr 1, 2024· 1 reaction

    Just LoRA is enough.

    4037108Apr 15, 2024

    No comment…

    Sheldoncooper7765Apr 4, 2024· 14 reactions
    CivitAI

    Why do 90% of these images have nothing to do with Disney princesses from Wreck it Ralph.

    titansteng
    Author
    Apr 4, 2024· 1 reaction

    The model started with v1.0 featuring princesses from "Wreck-It Ralph." Later versions have included additional data from other sources. Maybe a bit too much. ;)

    Sheldoncooper7765Apr 4, 2024· 1 reaction

    @titansteng  I should clarify, 90% of the images that have this lora tagged don't have the lora anywhere in the prompt.

    titansteng
    Author
    Apr 4, 2024

    @Sheldoncooper7765 I have no idea on that.

    JohnnyB1Apr 5, 2024

    @Sheldoncooper7765 yeah they also dont really look like princesses that much, I wonder why people do this

    nymicalApr 6, 2024· 4 reactions

    @Sheldoncooper7765 Loras used in ComfyUI don't show up in prompt. There might be other programs as well that behave like this.

    3752548Apr 6, 2024

    I find this very fascinating aswell

    3752548Apr 6, 2024· 5 reactions

    I use it in all my generations for better results. It's just a damn good lora

    ditaApr 8, 2024· 19 reactions

    @Sheldoncooper7765 It's happening everywhere on CivitAI right now. People are uploading tons of images and tagging popular assets when they haven't used the assets at all. Something really needs to be done about it.

    smokewApr 18, 2024

    Gens are promoted this weird way.

    SuzuHoshiApr 25, 2024

    bot accounts to farm buzz

    Nuclear314May 3, 2024· 1 reaction

    This is a lora that has no trigger words so it doesn't need to be included in the prompt. Adding it alone is enough to make the lora work.

    NamelessOptimistFeb 5, 2025

    @dita On this note, I assumed Civitai themselves, if not the uploaders, just removed the calls to the LORAs they used for whatever reason. You also sometimes see groups of multiple commas where I presumed the LORA calls used to be, but again, have been removed and either put into the Civitai interface or hidden altogether. No REAL evidence for this though, just my first guess. Can anyone confirm that Civitai does or does not remove the <lora:somelora:1.0> call in the prompt when uploading?

    LORA
    SDXL 1.0

    Details

    Downloads
    135,374
    Platform
    CivitAI
    Platform Status
    Available
    Created
    11/30/2023
    Updated
    5/14/2026
    Deleted
    -

    Files

    dataset.zip

    Mirrors

    HuggingFace (1 mirrors)
    CivitAI (1 mirrors)