CivArchive
    Environmental Anime Style Mix (Makoto Shinkai) - H3 / LTX 2.3 - v1.0 H3
    NSFW

    H3:

    Trained on 228 screen captures from Makoto Shinkai's "Your Name". The dataset is entirely environmental shots, with a few people and very few close ups of people if any. Trained on 1536x864 resolution.

    Trigger word:

    2d anime style, art by makoto shinkai

    The base model is definitely trained on this movie, and probably a bunch of his other works. But I wanted to see if I could get more detail out of the environment. And I think it did sort of work in a way as a detailer. Things look more Shinkai rather than Ghibli now. You get a lot of the camera composition from shinkai as well, the lense flairs, the bokeh without mentioning them in the prompt. How environmental items are placed in the foreground. How the lighting works in animation etc. All that seems burned into the lora, which I think you could get out of the base model but this is more consistent. Character design though did find its way, there is only so many shots where people were in the dataset, but I think that's fine.

    I almost didn't upload this, because there isn't huge changes from the base model, mostly subtle. But I do like certain aspects, so I thought I'd share. Let me know what you think.

    LTX:

    Trigger words:

    ANIMSTY, SHW_YN.

    I took my 90's anime lora at 53K steps and trained on top of it 231 clips from Makoto Shinkai's "Your Name" an additional 11.5k steps. But all the dataset was only environmental shots. Landscapes, rooms, cityscapes, etc. basically anything not human focused. There are some crowd shots and some scenes do have people though. As a result the people are more in the 90s anime style design but the animation look and feel is more modern. The downside is that the model started to trend back towards a more "3D" look and motion on the people.

    This was mostly a test to see if a detailed work like Shinkai's could act a detailer for environments without too much negative effect on other aspects. And I think for the most part it worked, even the people's faces have more details. I think this dataset will work well mixed into a larger pool for a modern anime lora. Give it a try and let me know what you think.

    Description

    Trained on 228 screen captures from Makoto Shinkai's "Your Name". The dataset is entirely environmental shots, with a few people and very few close ups of people if any. Trained on 1536x864 resolution.

    Trigger word:
    2d anime style, art by makoto shinkai

    The base model is definitely trained on this movie, and probably a bunch of his other works. But I wanted to see if I could get more detail out of the environment. And I think it did sort of work in a way as a detailer. Things look more Shinkai rather than Ghibli now. You get a lot of the camera composition from shinkai as well, the lense flairs, the bokeh without mentioning them in the prompt. How environmental items are placed in the foreground. How the lighting works in animation etc. All that seems burned into the lora, which I think you could get out of the base model but this is more consistent. Character design though did find its way, there is only so many shots where people were in the dataset, but I think that's fine.

    FAQ

    Comments (4)

    kronos1959777Sep 6, 2026· 1 reaction
    CivitAI

    lol your file naming format sucks, but nice lora.

    KiraNuggetSep 6, 2026

    YOURCOMMENT_IsHillarious9500.lol

    dillion1920Sep 6, 2026

    I blame Civitai.

    I have seem like 10 V1's now, and that is just the one i clicked.

    Scene lacks rules.. bad scene. Need rules.

    tazmannner379
    Author
    Sep 7, 2026

    Its trained on the movie "your name" first version so v1, and the number of steps.

    LORA
    MiniMax H3

    Details

    Downloads
    388
    Platform
    CivitAI
    Platform Status
    Available
    Created
    9/6/2026
    Updated
    9/8/2026
    Deleted
    -
    Trigger Words:
    2d anime style, art by makoto shinkai

    Files

    YOURNAME_H3_V1-step00009900.safetensors

    Mirrors