Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization
- URL: http://arxiv.org/abs/2410.03190v1
- Date: Fri, 4 Oct 2024 07:05:16 GMT
- Title: Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization
- Authors: Zichen Miao, Zhengyuan Yang, Kevin Lin, Ze Wang, Zicheng Liu, Lijuan Wang, Qiang Qiu,
- Abstract summary: We present an algorithm named pairwise sample optimization (PSO), which enables the direct fine-tuning of an arbitrary timestep-distilled diffusion model.
PSO introduces additional reference images sampled from the current time-step distilled model, and increases the relative likelihood margin between the training images and reference images.
We show that PSO can directly adapt distilled models to human-preferred generation with both offline and online-generated pairwise preference image data.
- Score: 97.35427957922714
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Recent advancements in timestep-distilled diffusion models have enabled high-quality image generation that rivals non-distilled multi-step models, but with significantly fewer inference steps. While such models are attractive for applications due to the low inference cost and latency, fine-tuning them with a naive diffusion objective would result in degraded and blurry outputs. An intuitive alternative is to repeat the diffusion distillation process with a fine-tuned teacher model, which produces good results but is cumbersome and computationally intensive; the distillation training usually requires magnitude higher of training compute compared to fine-tuning for specific image styles. In this paper, we present an algorithm named pairwise sample optimization (PSO), which enables the direct fine-tuning of an arbitrary timestep-distilled diffusion model. PSO introduces additional reference images sampled from the current time-step distilled model, and increases the relative likelihood margin between the training images and reference images. This enables the model to retain its few-step generation ability, while allowing for fine-tuning of its output distribution. We also demonstrate that PSO is a generalized formulation which can be flexibly extended to both offline-sampled and online-sampled pairwise data, covering various popular objectives for diffusion model preference optimization. We evaluate PSO in both preference optimization and other fine-tuning tasks, including style transfer and concept customization. We show that PSO can directly adapt distilled models to human-preferred generation with both offline and online-generated pairwise preference image data. PSO also demonstrates effectiveness in style transfer and concept customization by directly tuning timestep-distilled diffusion models.
Related papers
- Plug-and-Play Diffusion Distillation [14.359953671470242]
We propose a new distillation approach for guided diffusion models.
An external lightweight guide model is trained while the original text-to-image model remains frozen.
We show that our method reduces the inference of classifier-free guided latent-space diffusion models by almost half.
arXiv Detail & Related papers (2024-06-04T04:22:47Z) - EM Distillation for One-step Diffusion Models [65.57766773137068]
We propose a maximum likelihood-based approach that distills a diffusion model to a one-step generator model with minimal loss of quality.
We develop a reparametrized sampling scheme and a noise cancellation technique that together stabilizes the distillation process.
arXiv Detail & Related papers (2024-05-27T05:55:22Z) - Distilling Diffusion Models into Conditional GANs [90.76040478677609]
We distill a complex multistep diffusion model into a single-step conditional GAN student model.
For efficient regression loss, we propose E-LatentLPIPS, a perceptual loss operating directly in diffusion model's latent space.
We demonstrate that our one-step generator outperforms cutting-edge one-step diffusion distillation models.
arXiv Detail & Related papers (2024-05-09T17:59:40Z) - Training Class-Imbalanced Diffusion Model Via Overlap Optimization [55.96820607533968]
Diffusion models trained on real-world datasets often yield inferior fidelity for tail classes.
Deep generative models, including diffusion models, are biased towards classes with abundant training images.
We propose a method based on contrastive learning to minimize the overlap between distributions of synthetic images for different classes.
arXiv Detail & Related papers (2024-02-16T16:47:21Z) - Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation [59.184980778643464]
Fine-tuning Diffusion Models remains an underexplored frontier in generative artificial intelligence (GenAI)
In this paper, we introduce an innovative technique called self-play fine-tuning for diffusion models (SPIN-Diffusion)
Our approach offers an alternative to conventional supervised fine-tuning and RL strategies, significantly improving both model performance and alignment.
arXiv Detail & Related papers (2024-02-15T18:59:18Z) - BOOT: Data-free Distillation of Denoising Diffusion Models with
Bootstrapping [64.54271680071373]
Diffusion models have demonstrated excellent potential for generating diverse images.
Knowledge distillation has been recently proposed as a remedy that can reduce the number of inference steps to one or a few.
We present a novel technique called BOOT, that overcomes limitations with an efficient data-free distillation algorithm.
arXiv Detail & Related papers (2023-06-08T20:30:55Z) - Variational Diffusion Models [33.0719137062396]
We introduce a family of diffusion-based generative models that obtain state-of-the-art likelihoods on image density estimation benchmarks.
We show that the variational lower bound (VLB) simplifies to a remarkably short expression in terms of the signal-to-noise ratio of the diffused data.
arXiv Detail & Related papers (2021-07-01T17:43:20Z)
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.