This was a LoRA made for a commission! My client was kind enough to let me share on CivitAI; thank you!

No trigger words! Just use the LoRA, suggested weight is 1.0-1.5.

You can also include "3d", "game graphics" but not required at all; the base model is great with Natural Language and long prompts; try to avoid tag based prompting.

Raw outputs from the Model + LoRA; NO upscaling or hires-fix.
ComfyUI Metadata is included in the sample images! Click the little icon in the bottom right to see it.

It was trained on 115 1024x1024 images scraped from the internet and extracted from game files.