Authors
- Dongjun Kim*
- Chieh-Hsin Lai
- Wei-Hsiang Liao
- Naoki Murata
- Yuhta Takida
- Toshimitsu Uesaka
- Yutong He
- Yuki Mitsufuji
- Stefano Ermon*
* External authors
Venue
- ICLR 2024
Date
- 2024
Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
Dongjun Kim*
Yutong He
Stefano Ermon*
* External authors
ICLR 2024
2024
Abstract
Consistency Models (CM) (Song et al., 2023) accelerate score-based diffusion model sampling at the cost of sample quality but lack a natural way to trade-off quality for speed. To address this limitation, we propose Consistency Trajectory Model (CTM), a generalization encompassing CM and score-based models as special cases. CTM trains a single neural network that can -- in a single forward pass -- output scores (i.e., gradients of log-density) and enables unrestricted traversal between any initial and final time along the Probability Flow Ordinary Differential Equation (ODE) in a diffusion process. CTM enables the efficient combination of adversarial training and denoising score matching loss to enhance performance and achieves new state-of-the-art FIDs for single-step diffusion model sampling on CIFAR-10 (FID 1.73) and ImageNet at 64X64 resolution (FID 2.06). CTM also enables a new family of sampling schemes, both deterministic and stochastic, involving long jumps along the ODE solution trajectories. It consistently improves sample quality as computational budgets increase, avoiding the degradation seen in CM. Furthermore, CTM's access to the score accommodates all diffusion model inference techniques, including exact likelihood computation.
Related Publications
In music production, manipulating audio effects (Fx) parameters through natural language has the potential to reduce technical barriers for non-experts. We present LLM2Fx, a framework leveraging Large Language Models (LLMs) to predict Fx parameters directly from textual desc…
This paper explores the use of unlearning methods for training data attribution (TDA) in music generative models trained on large-scale datasets. TDA aims to identify which specific training data points contributed to the generation of a particular output from a specific mod…
General-purpose audio representations have proven effective across diverse music information retrieval applications, yet their utility in intelligent music production remains limited by insufficient understanding of audio effects (Fx). Although previous approaches have empha…
JOIN US
Shape the Future of AI with Sony AI
We want to hear from those of you who have a strong desire
to shape the future of AI.