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
Chroma version trained on the V2 Dataset .
Works better than the Original Flux V2 Flux on Chroma.
FAQ
Comments (10)
Works very well for cinematic rendering( wan2.2 T2V) not necessary 80s , check my viking woman ;)
Castle Rat! 🤘🏰🐀⚔️
FOR THE REALM!!!
Your Lora doesn't work with other Loras. How do you stack loras for Z-image to make it work?
https://civitai.com/posts/24943333
Here a sample of it working with other LoRA. Same prompt - No LoRAs, each of the 2 LoRAs by itself, both of them at the same time.
In ComfyUI used CRT Nodes and power Loader and I saw no issues. If you post something and send me a link I will check it when I have time.
A lot of stuff in Comfy/Training is Experimental or changing all the time, so you (or I) might be using broken version of something.
@ArsMachina have another workflow example? these are different.
@QIko Honestly not sure what you mean friend. Are you having an issue with an old version?
I gave you example of LoRA stack on Civit for ZIT.
If you use ComfyUI I would recommend Power Lora Loader (rgthree). Or post something here to show me what does not work for you and link it.
@ArsMachina Which CRT nodes do you need?
@rsflipson2 At this point you don't need anything special. Just Update Comfy to the latest version. When I Initially released the model there was no support yet.
the lora definately works with other loras. its z-image thats your route cause of the problem. it cant handle multiple loras at full strength.... things just get bloated and artifacty. i suggest running whatever lora stack you have to ADD UP to 1.0 strength.
so if your using 2 loras try:
lora 1 - 0.4 strength
lora 2 - 0.6 strength
or 0.5 and 0.5 and so on
this seems to fix all my issues i had when testing lora stacks.
hope this helps <3