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:
Your favourite spot.
Listen to Castle Rat as background.
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
Trained on the V2 Dataset with default Settings in AI Toolkit.
You can up the Strength to 1.5 without issues.
I have enabled 1000 "Free Trail" Images for On Site Generation , so go Nuts :)
FAQ
Comments (3)
I love all of these, but the Wan version is really unique. It's fascinating.
Wan as a whole is AMAZING model for T2I.
I thinkt that it actually might be the best T2I , but just not that many people actively use it.
@ArsMachina Sadly, Wan is really painful to use on older computers like mine compared to most models. I can get 4 preview pictures in a minute with SDXL, wan T2I takes me 9+minutes for a single output.