Download
1 variant available
3820 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
4.5K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
9180 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
(39)
Jul 11, 2024
Works without the trigger words ArsMJStyleAnime, but gives stronger results with them.
Works great in the 0.3 - 1 range, depending on the Lora Stack you use.
The training images are really sharp , so you can go pretty high and still get a coherent images.
Above 1.2 everything starts getting abstract.
I recommend starting in the 0.8 - 1 range
For more "Fantasy whimsical" you can try Style A. Link in the resources.
Show more

1.1K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
6.5K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
46K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9K

Created on Civitai
License:
CreativeML Open RAIL++-MFlux Update - Flux LoRA was created with the Rapid Flux Training.
The Lora is trained on MidJourney Images that use my "Personalised Style" + a really sharp Style that Midjourney describe as Noir Luminescence.
The trigger words are ArsMJStyle, NoirLuminescence
The training images are really sharp , so you can go pretty high and still get a coherent images.
Works great in the 0.3 - 1.5 range, depending on the Lora Stack you use.


