View publication

Diffusion models have demonstrated excellent potential for generating diverse images. However, their performance often suffers from slow generation due to iterative denoising. Knowledge distillation has been recently proposed as a remedy that can reduce the number of inference steps to one or a few without significant quality degradation. However, existing distillation methods either require significant amounts of offline computation for generating synthetic training data from the teacher model or need to perform expensive online learning with the help of real data. In this work, we present a novel technique called BOOT that overcomes these limitations with an efficient data-free distillation algorithm. The core idea is to learn a time-conditioned model that predicts the output of a pre-trained diffusion model teacher given any time step. Such a model can be efficiently trained based on bootstrapping from two consecutive sampled steps. Furthermore, our method can be easily adapted to large-scale text-to-image diffusion models, which are challenging for conventional methods given the fact that the training sets are often large and difficult to access. We demonstrate the effectiveness of our approach on several benchmark datasets in the DDIM setting, achieving comparable generation quality while being orders of magnitude faster than the diffusion teacher. The text-to-image results show that the proposed approach is able to handle highly complex distributions, shedding light on more efficient generative modeling.

Related readings and updates.

Enhancing Paragraph Generation with a Latent Language Diffusion Model

In the fast-evolving world of natural language processing (NLP), there is a strong demand for generating coherent and controlled text, as referenced in the work Toward Controlled Generation of Text. Traditional autoregressive models such as GPT, which have long been the industry standard, possess inherent limitations that sometimes manifest as repetitive and low-quality outputs, as seen in the work The Curious Case of Neural Text Degeneration. This is primarily due to a phenomenon known as "exposure bias," as seen in the work Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks. This imperfection arises due to a mismatch between how these models are trained and their actual use during inference, often leading to error accumulation during text generation.

See highlight details

TRACT: Denoising Diffusion Models with Transitive Closure Time-Distillation

Denoising Diffusion models have demonstrated their proficiency for generative sampling. However, generating good samples often requires many iterations. Consequently, techniques such as binary time-distillation (BTD) have been proposed to reduce the number of network calls for a fixed architecture. In this paper, we introduce TRAnsitive Closure Time-distillation (TRACT), a new method that extends BTD. For single step diffusion,TRACT improves FID…
See paper details