This LORA for background.
I created datasets based on Z1os's images & prompt (thx Z1os). LORA was created with fluxgym (RTX-4090).
12 scenes:
junkyard (main scene) ,
office-workshop inside,
junkyard workshop scene,
junkyard alleyway between containers,
nighttime scene in a junkyard with campfire,
post-apocalyptic old bar,
deteriorated post-apocalyptic laundry,
opened shipping containers interior scene,
inside a weathered container,
communal living space,
communal meal scene inside a ramshackle junkyard kitchen-workshop,
post-apocalyptic junkyard with upholstered sofa in strong sunlight.
Description
LORA was created base on 72 datasets images with fluxgym.
I trained this LoRA using a prompt-addressable implicit spatial representation. It functions as a text-based scene-control system: location + sub-theme + object + spatial relation + viewpoint + interaction.
Triggers: junky4rd, sh1pp1ngc0nt41n3rs, 0ff1c3w0rksh0p, c0nt41n3r1ns1d3, w0rksh0p, c0mmun4lsp4c3, 4ll3yw4y, k1tch3n, n1ghtt1m3, s0fasun, 0ldb4r, l4udry