Truncated Consistency Models
- URL: http://arxiv.org/abs/2410.14895v1
- Date: Fri, 18 Oct 2024 22:38:08 GMT
- Title: Truncated Consistency Models
- Authors: Sangyun Lee, Yilun Xu, Tomas Geffner, Giulia Fanti, Karsten Kreis, Arash Vahdat, Weili Nie,
- Abstract summary: Training consistency models requires learning to map all intermediate points along PF ODE trajectories to their corresponding endpoints.
We empirically find that this training paradigm limits the one-step generation performance of consistency models.
We propose a new parameterization of the consistency function and a two-stage training procedure that prevents the truncated-time training from collapsing to a trivial solution.
- Score: 57.50243901368328
- License:
- Abstract: Consistency models have recently been introduced to accelerate sampling from diffusion models by directly predicting the solution (i.e., data) of the probability flow ODE (PF ODE) from initial noise. However, the training of consistency models requires learning to map all intermediate points along PF ODE trajectories to their corresponding endpoints. This task is much more challenging than the ultimate objective of one-step generation, which only concerns the PF ODE's noise-to-data mapping. We empirically find that this training paradigm limits the one-step generation performance of consistency models. To address this issue, we generalize consistency training to the truncated time range, which allows the model to ignore denoising tasks at earlier time steps and focus its capacity on generation. We propose a new parameterization of the consistency function and a two-stage training procedure that prevents the truncated-time training from collapsing to a trivial solution. Experiments on CIFAR-10 and ImageNet $64\times64$ datasets show that our method achieves better one-step and two-step FIDs than the state-of-the-art consistency models such as iCT-deep, using more than 2$\times$ smaller networks. Project page: https://truncated-cm.github.io/
Related papers
- Stable Consistency Tuning: Understanding and Improving Consistency Models [40.2712218203989]
Diffusion models achieve superior generation quality but suffer from slow generation speed due to iterative nature of denoising.
consistency models, a new generative family, achieve competitive performance with significantly faster sampling.
We propose a novel framework for understanding consistency models by modeling the denoising process of the diffusion model as a Markov Decision Process (MDP) and framing consistency model training as the value estimation through Temporal Difference(TD) Learning.
arXiv Detail & Related papers (2024-10-24T17:55:52Z) - One Step Diffusion via Shortcut Models [109.72495454280627]
We introduce shortcut models, a family of generative models that use a single network and training phase to produce high-quality samples.
Shortcut models condition the network on the current noise level and also on the desired step size, allowing the model to skip ahead in the generation process.
Compared to distillation, shortcut models reduce complexity to a single network and training phase and additionally allow varying step budgets at inference time.
arXiv Detail & Related papers (2024-10-16T13:34:40Z) - ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models [59.90959789767886]
We show that optimizing consistency training loss minimizes the Wasserstein distance between target and generated distributions.
By incorporating a discriminator into the consistency training framework, our method achieves improved FID scores on CIFAR10 and ImageNet 64$times$64 and LSUN Cat 256$times$256 datasets.
arXiv Detail & Related papers (2023-11-23T16:49:06Z) - Improved Techniques for Training Consistency Models [13.475711217989975]
We present improved techniques for consistency training, where consistency models learn directly from data without distillation.
We propose a lognormal noise schedule for the consistency training objective, and propose to double total discretization steps every set number of training iterations.
These modifications enable consistency models to achieve FID scores of 2.51 and 3.25 on CIFAR-10 and ImageNet $64times 64$ respectively in a single sampling step.
arXiv Detail & Related papers (2023-10-22T05:33:38Z) - Multi-timestep models for Model-based Reinforcement Learning [10.940666275830052]
In model-based reinforcement learning (MBRL), most algorithms rely on simulating trajectories from one-step dynamics models learned on data.
We tackle this issue by using a multi-timestep objective to train one-step models.
We find that exponentially decaying weights lead to models that significantly improve the long-horizon R2 score.
arXiv Detail & Related papers (2023-10-09T12:42:39Z) - Score Mismatching for Generative Modeling [4.413162309652114]
We propose a new score-based model with one-step sampling.
We train a standalone generator to compress all the time steps with the gradient backpropagated from the score network.
In order to produce meaningful gradients for the generator, the score network is trained to simultaneously match the real data distribution and mismatch the fake data distribution.
arXiv Detail & Related papers (2023-09-20T03:47:12Z) - Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be
Consistent [97.64313409741614]
We propose to enforce a emphconsistency property which states that predictions of the model on its own generated data are consistent across time.
We show that our novel training objective yields state-of-the-art results for conditional and unconditional generation in CIFAR-10 and baseline improvements in AFHQ and FFHQ.
arXiv Detail & Related papers (2023-02-17T18:45:04Z) - ProDiff: Progressive Fast Diffusion Model For High-Quality
Text-to-Speech [63.780196620966905]
We propose ProDiff, on progressive fast diffusion model for high-quality text-to-speech.
ProDiff parameterizes the denoising model by directly predicting clean data to avoid distinct quality degradation in accelerating sampling.
Our evaluation demonstrates that ProDiff needs only 2 iterations to synthesize high-fidelity mel-spectrograms.
ProDiff enables a sampling speed of 24x faster than real-time on a single NVIDIA 2080Ti GPU.
arXiv Detail & Related papers (2022-07-13T17:45:43Z) - Decoupled Multi-task Learning with Cyclical Self-Regulation for Face
Parsing [71.19528222206088]
We propose a novel Decoupled Multi-task Learning with Cyclical Self-Regulation for face parsing.
Specifically, DML-CSR designs a multi-task model which comprises face parsing, binary edge, and category edge detection.
Our method achieves the new state-of-the-art performance on the Helen, CelebA-HQ, and LapaMask datasets.
arXiv Detail & Related papers (2022-03-28T02:12:30Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.