CivArchive
    Retro 90's Anime Style Lora LTX-2.3 - v1.0
    NSFW

    The purpose of this lora is to create a general anime style lora for anime from the 90's.

    V2 info:

    Trained on 12 different anime's from the 90s. A total of 766 clips. Each show has it's own trigger word and there is a general trigger word that's in all captions. I recommend using the ANIMSTY trigger word at minimum. If style doesn't trigger. As a last resort use "anime" at end of the prompt but I think it will make the output not as good.

    General Trigger word: ANIMSTY

    Source Trigger-Word

    Akira: SHW_AKIRA

    Cowboy bebop: SHW_CWBY

    Evangelion: SHW_EVA

    GitS: SHW_GITS

    Goldenboy: SHW_GLBY

    Gunbuster: SHW_GNBR

    Kite: SHW_KTE

    Outlawstar: SHW_OUT

    Perfectblue: SHW_PFTBL

    Slayers: SHW_SLYR

    Tenchi Universe: SHW_TNCH

    Irresponsible Captain Tylor: SHW_TYL

    This lora should give not just the style of the atheistic of 90's anime, it will also bring the motion. (The base model of LTX basically gives you 3D style motion, this gives it a more 2D anime style). You may lose some things like camera control as the dataset has pretty static camera beyond camera pans.

    Since this model is trained on a large variety of data (50-100 clips per show), you can use it as a base to train future anime loras. But maybe it might not work so well with modern anime. I might do a modern anime one next.

    You can access the save state files on my hugging face here. Download the folder and then do this argument on musubi tuner fork: --resume "/PATH/anime90s/anime90s-step00040000-state". And use your own anime dataset from another show and train it to that show's style as a shortcut. This took around 40 hours of training to reach this state on a 5090 locally. I also will attach some sample data and my training configs. Feel free to ask if you need help.

    https://huggingface.co/comfyuiman/anime90s_ltx/tree/main/anime90s-step00040000-state

    https://huggingface.co/comfyuiman/anime90s_ltx/tree/main/anime90s-step00053000-state

    I'd love feedback on this. I think I will do a modern anime style lora next. Then maybe try a fine tune of the actual model with more data. (long-term future goal).

    I recommend using my example workflow, and its best on 50FPS, though 24FPS is ok too.

    OLD:

    The purpose of this lora is to create a general anime style lora for anime from the 90's. It's trained on 5 different anime from that era. It's goal is not just aesthetics but also to teach the motion of 2d anime from that era since its trained entirely on clips.

    This lora was trained for the hackathon at ados paris (https://ados.events/). So the preparation was a bit messy due to the 8 or so hour timelimit. And a lot of issues which will be fixed in v2. But it was more of a proof of concept and its in good enough shape to release to public. All samples are t2v.

    The dataset

    Akira 75 clips

    Cowboy Bebop 60 clips

    Ghost in the shell (movie) 50 clips

    Perfectblue 60 clips

    Irresponsible Captain Tylor 60 clips

    Total 305 clips

    I used pyscene to split these into clips between 9-121 frames and converted them 25fps

    I forgot to separate Cowbebop into its own group and as a result sometimes you get black bars on 16:9 generations (because my source for that was 4:3). This will be fixed in the next version. I wanted to do 10 shows and 700 clips but I ran out of time. So next version will have more variety of data source. And I might do 100 clips per show. As usual I captioned without mentioning the style to remove bias from the base model which doesn't understand so well.

    Training

    I was going to train on H100 but I couldn't get the instance working so I trained locally on my 5090. I will provide sample training data and config files later. The training resolution was 832x480 and max 121 frames. I used default LR and trained video only. I used rank 64. I trained to around 18k steps, but I like the result of 14k steps the most. But I didn't have much time to check earlier checkpoints between 8-13k steps.

    Prompting

    Use the style trigger word ANIMSTY to trigger the style.

    I also have trigger words for each source material:

    SHW_AKIRA, SHW_GITS, SHW_TYL, SHW_CWBY, SHW_PFTBL

    The theory is that you combine the main styler trigger with a show trigger word and it will lean the model to generate in that shows style or you can remix by adding both. Or exclude show keyword for more general look. I need more time to test if that is the case, but I think maybe not. Give it a try.

    For the most part it should trigger as anime style without any style keywords. But if that fails you can add "anime" to the end but I recommend only doing it as a last resort. Most of my prompts did not need it at 14K steps. And again sorry for black bars that may appear, it will be fixed in v2.

    I recommend using my recommend workflow and 50fps.

    Description

    FAQ

    Comments (11)

    MikeflowerApr 20, 2026· 2 reactions
    CivitAI

    😍 👍🏻

    distai817Apr 20, 2026· 1 reaction
    CivitAI

    FYI - For me this LoRA is listed with an incorrect SHA256 603AF6DB2B654DF938278CCAB3393E4E60F6BBDA8B389833EEFAB5F675F37596 in Cicitai webpage!!

    This results in LoRA Manager downloading examples from some other LoRA.

    If I edit the LoRA Manager .json file to have the correct SHA256 834a9053c167c68673c1a008a42eadc1097e8ac43f2219cccec7ca2cf8946f0d and then download example images, it is fixed.

    This looks to only be an issue with Civitai and no issue with this LoRA. Civitai server needs to re-hash it somehow?

    tazmannner379
    Author
    Apr 20, 2026

    Do i need to re-upload it?

    distai817Apr 20, 2026

    @tazmannner379 naah, I think Civitai is having an issue. I have now also found other LoRAs with same duplicate hash listed.

    tazmannner379
    Author
    Apr 20, 2026

    @distai817 ok cool, yeah there is a lot of issues now in civitai

    GooodisApr 20, 2026
    CivitAI

    Does it have any effect using it for i2v? As in maybe affecting the animation/moiton?

    tazmannner379
    Author
    Apr 20, 2026

    I haven't tested it but my last anime ltx lora I was told it made the motion more like anime. That said its trained t2v layers so works in a limited capacity for i2v. Give it a try

    tazmannner379
    Author
    Apr 24, 2026· 7 reactions
    CivitAI

    V2 is cooking, more than x2 dataset and 12 difference movies/shows sourced.

    tazmannner379
    Author
    Apr 25, 2026· 1 reaction

    I tried to post V2 but it got 404, and then I tried again but with no write up. So it may post it with no context. I'll try again tomorrow, hope civitai fixes itself

    sirdrakApr 26, 2026· 1 reaction

    @tazmannner379 Over the last three days, it seems some things aren't working correctly on Civitai... One is what you mentioned, and another I've noticed is that the number of downloads and likes for the models isn't being recorded. I think it's related to the double buzz promotion, because the problems coincide in time with that promotion.

    tazmannner379
    Author
    Apr 26, 2026· 1 reaction

    V2 is out, I've kept training though, and I'm at 53K steps right now and it still looks like its getting better. So we might have a V2.1 in a few days.

    LORA
    LTXV 2.3
    by tazmannner379
    Download (Beta) View on CivitAI
    style

    Details

    Downloads
    407
    Platform
    CivitAI
    Platform Status
    Available
    Created
    4/19/2026
    Updated
    5/23/2026
    Deleted
    -
    Trigger Words:
    SHW_AKIRA, SHW_GITS, SHW_TYL, SHW_CWBY, SHW_PFTBL
    ANIMSTY

    Files

    90sanime-ltx23-step00014000.comfy.safetensors

    Size:
    672.53 MB
    SHA256:
    603af6db2b654df938278ccab3393e4e60f6bbda8b389833eefab5f675f37596

    Mirrors

    CivitAI (169 mirrors)

    90sanime-ltx23-step00014000.comfy.safetensors

    Size:
    672.53 MB
    SHA256:
    603af6db2b654df938278ccab3393e4e60f6bbda8b389833eefab5f675f37596

    Mirrors

    CivitAI (169 mirrors)