metadata
library_name: audio-interv
tags:
- ace-step
- activation-steering
- audio
- caa
- diffusion
- interpretability
- music
- steering
- vocal-style
CAA — vocal_style (ACE-Step)
Steering vectors for the vocal_style concept on ACE-Step, computed via contrastive activation addition (CAA).
Paper
TADA! Tuning Audio Diffusion Models through Activation Steering — https://huggingface.co/papers/2602.11910
Quickstart
from src.steering import SteerableACEModel, CAASteeringController
model = SteerableACEModel(device="cuda")
model.pipeline.load()
ctrl = CAASteeringController.from_pretrained("lukasz-staniszewski/ace-step-caa-vocal-style", alpha=20.0)
with model.steer(ctrl):
audio = model.generate(
prompt="instrumental music", lyrics="[inst]",
audio_duration=10.0, infer_step=30, manual_seed=0,
)
Generation config
{
"method": "standard_caa",
"concept": "vocal_style",
"lyrics": "",
"num_cfg_passes": 2,
"save_all_cfg_passes": true,
"audio_duration": 30.0,
"num_inference_steps": 30,
"seed": 10,
"device": "cuda",
"save_dir": "steering_vectors/caa",
"guidance_scale_text": 0.0,
"guidance_scale_lyric": 0.0,
"guidance_scale": 5.0,
"guidance_interval": 1.0,
"guidance_interval_decay": 0.0
}