CivArchive
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined

    Train LoRa is time and resource expensive, you can support my future works here:

    it would be great if you could show some results of your work as a post/review

    Ore no Imouto ga Konnani Kawaii Wake ga Nai

    (俺の妹がこんなに可愛いわけがない)

    list will be updated later.

    Why my LoRa's? Because it's close to anime style, and this style is ~simple in details and can change without mutating target style more easy than artistic one. And it's hard to get quality anime style pictures from LoRa's with more artistic dataset with gradients and complex lighting.

    Description

    this is just first attempt, both will be rework later in different LoRA

    FAQ

    Comments (8)

    randomizer89
    Author
    Jun 6, 2023· 3 reactions
    CivitAI

    Kirino & Kyousuke LoRA is bad

    we can assume that this is a stub, normal LoRA

    on this title will not be until Friday, because remembering (having looked at the materials) the title, I decided to do it all the same in a complex / high-quality version.

    Suluman45Jun 7, 2023

    Question. How do we put kirino and her brother in the same image?

    randomizer89
    Author
    Jun 7, 2023· 1 reaction

    @Suluman45 i know only one way - dark magic of made multiple images and choice ~conditionally acceptable of them.
    "<lora:Oreimo_kousaka kirino, kousaka kyousuke:0.7> kousaka kirino, kousaka kyousuke, 1boy, 1girl, hug, 8k, masterpiece, absurdres, anime," positive from one of my tryes. i think it better if you change it to like:

    "<lora:Oreimo_kousaka kirino, kousaka kyousuke:0.7> 1girl, kousaka kirino, <action>,1boy, kousaka kyousuke, 8k, masterpiece, absurdres, anime,"

    but its work bad ofcourse, AI bad at multiple characters on one image.

    randomizer89
    Author
    Jun 13, 2023

    I'm really sorry for being so slow, i get some flu, and i watch this anime from first episode to last and thinking about how to made it... And i want to made it in right way. Slow on a week lol.

    OtherPerspectiveJun 22, 2023

    huh?

    randomizer89
    Author
    Jun 22, 2023

    @OtherPerspective huh?

    atmogenicJul 11, 2023· 1 reaction

    @Suluman45 if you're using AUTOMATIC1111 you'd get the extension called Regional prompter and with that it will cut the image up and allow you to add two characters within one image together for the AI to understand you want these 2 characters together

    https://github.com/hako-mikan/sd-webui-regional-prompter

    Suluman45Jul 11, 2023

    @atmogenic I use google collab to get on stable diffusion