CivArchive
    Preview 30936094
    Preview 30933951
    Preview 30933958
    Preview 30933825
    Preview 30933946
    Preview 30936095
    Preview 30933949

    This LoRA is designed to capture the distinct look and feel of early 80s fantasy movies.

    The trigger words are ArsMovieStill, 80s Fantasy Movie Still

    Z-IMAGE UPDATE:
    V2 dataset officially became my go-to test dataset when training a model for the first time.
    Experimental!

    Default ComfyUI LoRA Loader Reports Errors, but actually applys the LoRA.


    Recommended usage settings:

    1. Your favourite spot.

    2. Listen to Castle Rat as background.

    3. Enjoy!




    MJ7 UPDATE:
    Building each dataset is a joy, so with the release of MidJourney 7, I naturally started this one again from scratch.

    This version stays true to the original aesthetic but with improved fidelity and an even stronger 80s vibe.

    It’s trained on a fresh, carefully curated set of ~250 images, created by referencing the best results from the previous versions.


    V3 UPDATE:
    The training dataset has been further expanded to 1,000 curated images, pushing it to the limits of Civit’s on-site training capabilities.

    This update include broader selection of fantasy environments, mythical creatures, and epic scenes, enhancing the fidelity to the iconic 80s fantasy aesthetic.

    V2 UPDATE:
    Added to the dataset a huge amount of Fantasy Characters, beasts and scenes.

    Use v1 for stronger effects and v2/v3 for better versatility.

    Description

    FAQ

    Comments (7)

    search_botSep 28, 2024· 5 reactions
    CivitAI

    Awesome style!

    sdf34gdssdg4Sep 28, 2024· 6 reactions
    CivitAI

    They look like they all have the same face somehow.

    ArsMachina
    Author
    Sep 28, 2024

    Most LoRAs have "default" face it leans toward, if you don't add any description . Here it is just much more visible as the aesthetic is really specific and it pops out.

    sdf34gdssdg4Sep 29, 2024

    @ArsMachina Don't take me wrong, it looks gorgeous. I'm wondering if there's a way to alleviate this problem.

    ArsMachina
    Author
    Sep 29, 2024· 2 reactions

    @sdf34gdssdg4 Don't worry I don't take it as something negative :) I plan to extend this dataset at some point to ~700-1000 images and will have less people there , so the "default face" should not be as prominent .
    As for now you can try:
    Lowering the LoRA weight (0.4-0.6 still gives good results)
    Don't use the trigger words
    Add facial / race description for more diverce characters
    Different background setting description also tend to produce different characters

    547687Sep 29, 2024· 5 reactions
    CivitAI

    This Lora is magnificent. Thank you so much for making.

    anomedraSep 30, 2024· 8 reactions
    CivitAI

    I'm having a lot of fun with this one. Thank you for making a Pony version. :)

    LORA
    SDXL 1.0

    Details

    Downloads
    820
    Platform
    CivitAI
    Platform Status
    Available
    Created
    9/23/2024
    Updated
    5/12/2026
    Deleted
    -
    Trigger Words:
    ArsMovieStill, 80s Fantasy Movie Still