This LORA is intended to reproduce the style of in-game graphics of Silent Hill (1999) for the PlayStation. It was not trained on the FMV cut-scenes.
Suggested prompt: "sh1ps1 screenshot of "
I'd recommend a strength of 1.5 to 1.9 for decent in-game looking results.
Trained using fluxgym.
This is my first crack on publishing a LORA. Please be gentle 🤣
Description
Trained on 19 images. Mostly picked from the in-game cut-scenes so that I could eliminate any HUD elements and not have the screenshots include any one particular subject. I used minimal natural language captioning that I typed myself. I'd like to work on training a v2 in the future with a better dataset and better captions. v1 is more of an experiment.
I'd recommend a strength of 1.5 to 1.9 for decent in-game looking results.
Trained using fluxgym with a learning rate of 1.5e-4. Using the article by CrasH for guidance.