CivArchive
    Koda Mami - Lost Judgment (3d) - v1.0
    NSFW
    Preview 6423031
    Preview 6423069
    Preview 6422980
    Preview 6422979
    Preview 6423245

    to keep close to her old design try any of these - or put in Neg to reduce chance - SFW/NSFW

    1. may need to add 3d, or realistic, in neg for certain 2d/anime styles due to having more 3d image training - or lower weight for less influence -

    face/body

    koda, brown eyes, black hair, --- twintails,

    • suggest twintails, in NEG if attempting hair changes

    Outfit

    blue jacket, striped bow, pleated skirt, or red skirt, or school uniform, --- black socks, shoes, --- black underwear, pantyhose,

    Description

    FAQ

    Comments (3)

    FireBlack85Feb 9, 2024
    CivitAI

    I have a suggestion that might interest you,I think your loras should make a jump to XL,I'm not talking about normal XL but XL with DPO implementation,the technology came out last month,the XL models that are being made with that technology understand almost any prompt perfectly and not only that but it can also replicate many characters from very famous video games and series perfectly,the loras of DOP styles and characters are very consistent and you can do many things just to prompts,concepts,good anatomy,good hands,expressions etc,it looks like magic, as you have already made some models you can try to make an XL with that technology and mix it with one of yours or maybe the Darksun,if you mix a model like the Pony diffusion XL with a base or mixed XL model that has a similar style to one of yours it should give you as a result a model with DPO implemented, there is a lot of information and data still to be studied but the idea is that you can make better and more flexible things,I will leave you a copy and paste of my previous post with information that you might find useful,you can take the liberty to try any of those models that have DPO in the list..

    (copy paste)

    here is a list of all the models that I have seen and tested that have DPO

    1-AutismMix SDXL

    https://civitai.com/models/288584?modelVersionId=324619 (all three of their model mixes have DPO)

    2-Confetti Comrade Mix

    https://civitai.com/models/280344/confetti-comrade-mix(here I had left some comments giving ideas to move the community forward, anyway I will leave my ideas in this post in case someone reads it and wants to know more about it)

    3-Js2Prony

    https://civitai.com/models/280321/js2prony

    4-Comradeship XL

    https://civitai.com/models/246299/comradeship-xl(my favorite so far)

    5-[0.8(ponyDiffusionV6XL_v6) + 0.2(reproginexl_v10)] > NAI 3 !

    https://civitai.com/models/263797/08ponydiffusionv6xlv6-02reproginexlv10-greater-nai-3

    6-Hassaku XL

    https://civitai.com/models/140272/hassaku-xl-sfwandnsfw-beta(this model understands prompts well but is not good at replicating characters without loras,the other models in the list including the Pony Diffusion V6 XL can replicate characters perfectly,even better than Loras already made in the civitai community)

    the list I just left have good implementation of (DPO) the idea of this post is that the creators already famous in civitai begin to implement this technology,98% of civitai models are mediocre but with this technology the existing models can make magic,genitals,legs,hands,expressions,poses, concepts etc make more sense with these models already named(Pony Diffusion V6 XL was the first to implement the technology to a XL model) but the ones already named here are of very good quality also it would be great to continue seeing models with many different styles and more polished in the future) researching I discovered that if you mix a model that already has(DPO) with another model already existing civitai gives results like these. ..the technology works very well with XL but as far as I can see very bad with 1.5(for the moment) I think the future this year is XL I think the other model and lora creators should all work for XL,it feels good when you put indications and you get almost everything as you want,that with 1.5 is impossible,I am using XL,without controlnet and without Lora I have had incredible results,the mixes with the DPO models I think it is better to do them in Comfyui,I hope this post can help you,there are many people who still don't know about the technology

    I took the time to test about 50 XL models and all were exactly the same as the 1.5,bad anatomy etc,in search of DPO models I did my tests by replicating famous characters,an effective way to test is using as a prompt:

    cammy,chun li,jinx,league of legends,etc,if characters like that replicate perfectly the model has DPO,if the replica of the character doesn't come out then it doesn't,the models in this list can replicate the characters already named and many many more,(just do your list of character tests)....

    PS:there are models in civitai that claim to have DPO and don't have them or are very bad,all of them were tested by me so I save you time

    here you can read the post of this page to know a little more about DPO

    https://civitai.com/models/242825/dpo-direct-preference-optimization-lora-for-xl-and-15-openrail

    True_Might
    Author
    Feb 9, 2024

    well most of this would be useful IF I knew how to make XL loras (and test them) and with the amount of loras I have re-training them would take ages. The best I can do is slap DPO into some merges but idk

    FireBlack85Feb 9, 2024

    @True_Might start by trying a model from the list with some of the loras with DPO implemented,the results at prompt of those models are pretty impressive,understand almost everything,you can make a mix of the ones you already have existing,I don't think you have to redo all your loras from 0,there are people who are making lora styles and concepts with DPO,I'm not telling you to use DPO for 1. 5 because really the results are very poor,but for XL it is too good to be true,you already have a lot of experience making loras so if you learn to implement DPO in your loras it won't take you so much time to update all your loras again,here for example this creator implemented DPO in a concept he already had https://civitai.com/user/ragnaroook/models

    this one did the same

    https://civitai.com/user/MidFR

    the point is that I don't think you have to re-create dataset from 0 but look for a way to implement DPO to what you already have,if you look at images made by Pony Diffusion or some other model of the ones I mentioned you may learn how to do it.

    here you have 3 XL models with semi realistic DPO that were published today

    2.5D_Prony

    https://civitai.com/models/298707/25dprony?modelVersionId=335499

    2.6D_Prony

    https://civitai.com/models/298908/26dprony?modelVersionId=335720

    2.7D_Prony

    https://civitai.com/models/298717/27dprony?modelVersionId=335508

    I have tried all three models and I love what they do.

    the base models already have enough characters that you can replicate just by putting the name of the character and where it belongs, you do not need prompts for everything, there are also many styles that are already integrated here a list that may be useful https://rentry.co/ponyxl_loras_n_stuff

    LORA
    SD 1.5

    Details

    Downloads
    358
    Platform
    CivitAI
    Platform Status
    Available
    Created
    2/9/2024
    Updated
    6/18/2026
    Deleted
    -
    Trigger Words:
    koda

    Files

    KodaMami-10LJv9.safetensors

    Mirrors

    CivitAI (1 mirrors)

    Available On (1 platform)

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