How to use ntc-ai/minimax-music3-concept-sliders with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("MiniMaxAI/MiniMax-Music-3", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("ntc-ai/minimax-music3-concept-sliders") prompt = "Same prompt and lyrics. Energy slider Off then Loud +1. Unidirectional lyric-hold LM." image = pipe(prompt).images[0]
