ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2506.11476
24
0

LiLAC: A Lightweight Latent ControlNet for Musical Audio Generation

13 June 2025
Tom Baker
Javier Nistal
    DiffM
ArXiv (abs)PDFHTML
Main:6 Pages
1 Figures
Bibliography:3 Pages
4 Tables
Abstract

Text-to-audio diffusion models produce high-quality and diverse music but many, if not most, of the SOTA models lack the fine-grained, time-varying controls essential for music production. ControlNet enables attaching external controls to a pre-trained generative model by cloning and fine-tuning its encoder on new conditionings. However, this approach incurs a large memory footprint and restricts users to a fixed set of controls. We propose a lightweight, modular architecture that considerably reduces parameter count while matching ControlNet in audio quality and condition adherence. Our method offers greater flexibility and significantly lower memory usage, enabling more efficient training and deployment of independent controls. We conduct extensive objective and subjective evaluations and provide numerous audio examples on the accompanying website atthis https URL

View on arXiv
@article{baker2025_2506.11476,
  title={ LiLAC: A Lightweight Latent ControlNet for Musical Audio Generation },
  author={ Tom Baker and Javier Nistal },
  journal={arXiv preprint arXiv:2506.11476},
  year={ 2025 }
}
Comments on this paper