CivArchive
    RealCartoon-Pony - V1
    NSFW
    Preview 22472656
    Preview 22472682
    Preview 22472668
    Preview 22472669
    Preview 22472674
    Preview 22472671
    Preview 22472670
    Preview 22472672
    Preview 22472677
    Preview 22472673
    Preview 22472675
    Preview 22472680
    Preview 22472679
    Preview 22472678
    Preview 22472683
    Preview 22472685
    Preview 22472684
    Preview 22472676
    Preview 22472686
    Preview 22719719

    Checkout my Mage.Space Exclusive model: RealCartoon - Mage

    Want to send some support? (send some at Ko-fi)

    Want to support via Mage.space?

    1. https://www.mage.space/play/f53002f3571974ceca1d6bc90c059942

    Scroll down for some prompt recommendations

    Welcome to the the RealCartoon-Pony edition. I hope you all enjoy it like the other RealCartoon Series checkpoints!! Looking forward to seeing what images you all come up with!!

    Prompt Settings:

    (These settings are for A1111 ):

    The below image is the top settings I recommend. I do not use a VAE normally as

    The VAE downloadable from the https://civarchive.com/models/257749/pony-diffusion-v6-xl was used.

    Below are the normal settings I did for the showcase prompt images.

    Some variation of course happens depending on the desired outcome (I.E. Landscape). I also like to make portrait 832 by 1216 as well.

    Sampling method I primarily use is Euler a, but DPM++ SDE Karra and DPM++ 2M Karras do well as well.

    A newer version of the Euler sampler (Advanced Euler by licyk) - https://github.com/licyk/advanced_euler_sampler_extension

    • This one does better on hands

    • Normally produces images faster

    Upscaler is either R-ESRGAN 4x+ or 4k-UltraSharp for most of my images when running HiRes.fix, but I did not run it in my showcase images.

    The Upscale settings will vary depending on your computer.

    Run ADetailer if subject is in the distance can sometimes fail at faces with distance people. Be careful if you have blurred subjects in backgrounds; as this can start "enhancing them" and thus mess with the overall look. Be careful with ADetailer as it can sometimes start changing faces that are in the background.

    If you are having problems running A1111 you can change the "webui-user.bat" settings to help (by right clicking and opening in notepad):

    • set COMMANDLINE_ARGS= --xformers

    If you do not have xformers or cannot install it, put the following instead:

    • set COMMANDLINE_ARGS= --disable-model-loading-ram-optimization --opt-sdp-no-mem-attention

    To install xformers: how to install xformers

    Prompt Recommendations:

    When it comes to prompts that is really up to you. Here is some advice:

    1. Please be careful on the strength you add to LoRas as this can affect the overall look with the checkpoint. Stronger does not always mean better. I normally run 0.4 - 1 strengths depending on the LoRa.

    2. What is first in your prompt has higher priority.

    3. Having parathesis increases a priority, but having everything in them is almost as good as typing without them.

    4. Subtle changes in a prompt (to include punctuation) can change the image

    5. The seed helps in producing similar images with similar software and settings. It does not guarantee the same image as even a difference in software (I.E. ComfyUI) or hardware can affect it.

    6. If you want a more cartoon look (at least with this checkpoint) use the following near the front of the prompt: Anime, Cartoon, painted, or comic. This does not guarantee a look depending on the version; but it will lean more that way. This also works for Realistic looks (Realistic, real, etc).

    7. If you want Safe for work or not nudity to show up then make sure you put the following in your negative prompt: nude, nudity, naked, NSFW, nipples. Of course if you have this in your actual prompt then it will more then likely do it.

    8. The following is what I normally run in a negative prompt:

      (bad quality:1.3),(worst quality:1.3),watermark,(blurry),5-funny-looking-fingers

    __________________________________________________________________________________________________

    License & Use

    This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.

    • 1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content.

    • 2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license.

    • 3. You may re-distribute the weights. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the modified CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully).

      Please read the full license here Stable Diffusion

    Use Restrictions:

    You agree not to use the Model or Derivatives of the Model:

    - In any way that violates any applicable national, federal, state, local or international law or regulation

    - For the purpose of exploiting, harming or attempting to exploit or harm minors in any way

    - To generate or disseminate verifiably false information and/or content with the purpose of harming others

    - To generate or disseminate personal identifiable information that can be used to harm an individual

    - To defame, disparage or otherwise harass others

    - For fully automated decision making that adversely impacts an individual’s legal rights or otherwise creates or modifies a binding, enforceable obligation

    - For any use intended to or which has the effect of discriminating against or harming individuals or groups based on online or offline social behavior or known or predicted personal or personality characteristics

    - To exploit any of the vulnerabilities of a specific group of persons based on their age, social, physical or mental characteristics, in order to materially distort the behavior of a person pertaining to that group in a manner that causes or is likely to cause that person or another person physical or psychological harm

    - For any use intended to or which has the effect of discriminating against individuals or groups based on legally protected characteristics or categories

    - To provide medical advice and medical results interpretation

    - To generate or disseminate information for the purpose to be used for administration of justice, law enforcement, immigration or asylum processes, such as predicting an individual will commit fraud/crime commitment (e.g. by text profiling, drawing causal relationships between assertions made in documents, indiscriminate and arbitrarily-targeted use).

    Terms of use:

    - You are solely responsible for any legal liability resulting from unethical use of this model(s)

    - If you use any of these models for merging, please state what steps you took to do so and clearly indicate where modifications have been made.

    Note:

    If you see any conflicts or corrections to be made, please let me know.


    Description

    Welcome to Version 1. I hope you all enjoy and share the images you create!!

    FAQ

    Comments (27)

    LucifaelAug 2, 2024· 2 reactions
    CivitAI

    I'm very excited! I'm a huge fan of the other earlier checkpoints! <3

    7whitefire7
    Author
    Aug 2, 2024· 1 reaction

    Hope you enjoy...looking forward to seeing what people create with it.

    2018cfhAug 2, 2024· 6 reactions
    CivitAI

    Very excited to see if civit will allow for onsite generation! Real Cartoon has been one of my favorites.

    7whitefire7
    Author
    Aug 2, 2024· 1 reaction

    Me too....I am curious how well it will do on the onsite generator as well. :)

    2018cfhAug 2, 2024· 1 reaction

    @7whitefire7 it will do fantastic. When I got on here it seemed every third image was made with a real cartoon model.

    Icey64Aug 3, 2024· 2 reactions
    CivitAI

    Omg!! My dream has come true! Thank you for making this 😍

    shirakottekuAug 3, 2024· 3 reactions
    CivitAI

    You did it again whitefire, one of the best merges Anime fans could have expected

    DraftsmanAug 5, 2024· 9 reactions
    CivitAI

    I have to admit, I was waiting for this Checkpoint ;-)

    "Real Cartoon" was the First CP I´ve used to create Images...and I´ve always loved it.

    Thank you, for creating a Pony-Version !

    Cheers,

    D.

    7whitefire7
    Author
    Aug 5, 2024

    :)

    stable_diffusion_espanolAug 11, 2024· 3 reactions
    CivitAI

    Great model!! Here you have my review in Spanish: https://youtu.be/vvZjbd5cxFI

    7whitefire7
    Author
    Aug 11, 2024· 1 reaction

    Thanks for the review!

    YafeetMasterAug 12, 2024· 2 reactions
    CivitAI

    Buenisimo!!. es un punto de control muy bien entrenado. a diferencia de muchos otros puntos de control, este si esta muy bien entrenado en lo que respecta a los pies. hace muy bien la forma de los pies y los dedos. hay que tener en cuenta que se recomienda usar a menos 35 pasos en adelante para que defina muy bien la forma de los pies y los dedos. buen punto de control para los amantes de pies 🤤👣👣👣👣

    tempan123Aug 12, 2024· 1 reaction
    CivitAI

    Great model :D

    As a comment, it seems that the model consumes more RAM than it should. I am using my usual ComfyUi WorkFlow and this doesn't happen with the other models. I might be wrong, but it's worth mentioning.

    ElBanditoAug 25, 2024· 11 reactions
    CivitAI


    Why do I get Asian girls? And if you indicate Asian women in a negative prom, your face immediately becomes ugly and your eyes are blue and dull, like a doll’s? Get normal European eyes, I can't bear to look at these Asian eyes.

    michaelchu135279Sep 14, 2024· 2 reactions

    Don't use it then. wtf? What a stupid comment

    Kevin0777Sep 10, 2024· 1 reaction
    CivitAI

    can I use this for my nsfw games / comics?

    7whitefire7
    Author
    Sep 10, 2024· 1 reaction

    Sure :)

    GigaByteWideSep 22, 2024· 3 reactions
    CivitAI

    Donated some buzz to you :D Back when I first started using CIVITAI, your Real Cartoon XLs were some of the first few I experimented with <3 I'm loving the quality of this Pony variant

    7whitefire7
    Author
    Sep 22, 2024

    :) ty

    51stABISep 24, 2024· 3 reactions
    CivitAI

    Really wish, this would be available for onsite generation.

    The output looks so great.

    ponyboiSep 25, 2024· 1 reaction
    CivitAI

    Please bring to on-site

    7whitefire7
    Author
    Sep 28, 2024

    I reached out and it is due to space limitations. They are working on increasing this but how long I do not know :(

    7whitefire7
    Author
    Sep 28, 2024
    Fox009Oct 5, 2024· 3 reactions
    CivitAI

    This is the best checkpoint, thank you! But are there any good ways or LORAs to help reduce the "same face" effect?

    SD_AI_2025Nov 13, 2024· 3 reactions

    There are about 20 billion Character LoRAs on Civitai and you wonder.... if there are LoRAs to change the face ? O,o

    lightning_fuelNov 29, 2024

    @hansolocambo it's more about kind of lora that would generate each time a new face if its included in the prompt and not using different loras for different characters

    Foundation68Feb 3, 2025· 2 reactions

    Use dynamic prompts. It's a great way to get variety if you let SD run gens in the background while doing other stuff.

    Checkpoint
    Pony

    Details

    Downloads
    6,942
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/2/2024
    Updated
    6/14/2026
    Deleted
    -

    Available On (1 platform)

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