Thorra Anime Lora Lite (flux edition)
as seen in SDXL: https://civarchive.com/models/460522/thorra-sdxl-public

I decided to split the dataset into 3 separate Lora's.

• Main = 90's Anime Thorra Character Lora
  (Character Lora)

• Scene = 90's Anime Thorra
  (Megacity, Fortress Corridor, Airlock)

• Actions = 90's Anime "Thorra" Action Compositions
  (Rushing, Shooting)
  
  *scroll down for experimental modules*

Note: You can run the Main Lora alone, however it is designed to be reinforced by Scene and/or Actions

example, using Thorra Scenes only:

versus, loading the same prompt & seed with Thorra Main + Thorra Scenes at 0.6

Thorra Lite V2 is trained in rankdim 4-16

captions are in the training data for each release

Experimental Modules:
these are intended to extend Thorra-Main, or in a stack with other Thorra-Anima resources.
The aim to to produce tight estimations of consistent characters/locations.


Thorra-Airship-V1
- provides an airship generator for the Thorra Universe, as this is an illustration project.

Thorra-Machinecities-V1

• Provides machine city background locations

• Provides Floating machine city generator