CivArchive
    MidjourneyV3Artifacts - 512 SD1.5
    NSFW
    Preview 15598408
    Preview 15597846
    Preview 15598297
    Preview 15597852
    Preview 15598291
    Preview 15597851
    Preview 15598283
    Preview 15597853
    Preview 15597839
    Preview 15597844
    Preview 15597922
    Preview 15598353
    Preview 15598354
    Preview 15598497
    Preview 15598550
    Preview 15598498
    Preview 15599103
    Preview 15597848
    Preview 15598293
    Preview 15598295

    It seems like a long time ago when AI images were full of nightmarishly distorted renderings and unnameable mixtures, but I still like Midjourney v3, which appeared around the end of that era and was unique in its own way.

    Regarding this LoRA, it is basically not user-friendly (especially the SD 1.5 version). Sometimes people are not drawn, or multiple triggers may need to be emphasized in order to resemble the style.

    For the Pony version, it is recommended to use it with derivatives other than the original PonyDiffusionV6.

    AI画像といえば、描画が何もかも歪んでいたり名状しがたい物体ばかりだった時代もまるで昔の事みたいですが、Midjourney v3はそんな時代の最後らへんに現れて異彩を放っていた気がします。

    このLoRAは基本的に使い勝手が悪く(特にSD1.5版)、時々人物が出せなかったり、スタイルを似せるためにはいくつかトリガー的なタグを強調する必要があるかもしれません。

    Pony版については、オリジナルのPonyDiffusionV6以外の派生モデルでの使用をお勧めします。

    Description

    FAQ

    LORA
    SD 1.5

    Details

    Downloads
    128
    Platform
    CivitAI
    Platform Status
    Available
    Created
    6/13/2024
    Updated
    4/22/2026
    Deleted
    -

    Files

    mjv3_512-000008.safetensors

    Mirrors

    CivitAI (1 mirrors)