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
First Krea2 LoRAs batch incoming :) Based on V2 of the Dataset
Still playing with the parameters , but I think this is a really good starting point - Trained on the Raw Version with low+high noise (512 buckets only) split.
FAQ
Comments (7)
Yes, so glad to start seeing your Loras for Krea2!
Still Figuring out the best approach for my datasets, but I deffinately like the results so far. Will release few more next week.
@ArsMachina Amazing, looking forward to it.
Oh the double "__" in the name breaks it in forge neo if you have "dynamic prompts/wildcards" people don't put that in your loras :,(
I tested this in wan i2v and works very well!!
Krea seems the best to me. Probably with how well it captures styles. I really hope you update the 2000s/90s indie ones.
Thank you.
BTW always a good idea to just drop a line in the model you are missing with "I would like an X (Krea, Anima, etc) Version ". I usually try to do these first :)