OliBomby/Mapperatorinator-v32-LoRA-Voxell

LoRA: Voxell Techslider Style for Mapperatorinator

This is a LoRA (Low-Rank Adaptation) fine-tune for the OliBomby/Mapperatorinator-v32 model. It has been trained on a selection of maps by Voxell which are very slider heavy and technical. The result is this model will generally create many high-SV sliders and interesting slider shapes. It works best on technical or dubstep-like songs.

Model Details

• Base Model: OliBomby/Mapperatorinator-v32
• Model Type: LoRA

How to Use

You can load the LoRA directly from this repository without manually downloading the files. The script will handle it automatically. Recommended using year=null argument, because the source maps have no 'year' metadata.

1. Run Inference: Use the lora_path argument and set it to the name of this repository.

   python inference.py \
     audio_path='/path/to/your/audio.mp3' \
     output_path='/path/to/your/output_folder' \
     lora_path='mouceen/Mapperatorinator-v32-LoRA-Voxell' \
     year=null \
     ... # other arguments