Consistency Models

• URL: http://arxiv.org/abs/2303.01469v2
• Date: Wed, 31 May 2023 06:17:10 GMT
• Title: Consistency Models
• Authors: Yang Song, Prafulla Dhariwal, Mark Chen and Ilya Sutskever
• Abstract summary: We propose a new family of models that generate high quality samples by directly mapping noise to data. They support fast one-step generation by design, while still allowing multistep sampling to trade compute for sample quality. They also support zero-shot data editing, such as image inpainting, colorization, and super-resolution, without requiring explicit training.
• Score: 89.68380014789861
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion models have significantly advanced the fields of image, audio, and video generation, but they depend on an iterative sampling process that causes slow generation. To overcome this limitation, we propose consistency models, a new family of models that generate high quality samples by directly mapping noise to data. They support fast one-step generation by design, while still allowing multistep sampling to trade compute for sample quality. They also support zero-shot data editing, such as image inpainting, colorization, and super-resolution, without requiring explicit training on these tasks. Consistency models can be trained either by distilling pre-trained diffusion models, or as standalone generative models altogether. Through extensive experiments, we demonstrate that they outperform existing distillation techniques for diffusion models in one- and few-step sampling, achieving the new state-of-the-art FID of 3.55 on CIFAR-10 and 6.20 on ImageNet 64x64 for one-step generation. When trained in isolation, consistency models become a new family of generative models that can outperform existing one-step, non-adversarial generative models on standard benchmarks such as CIFAR-10, ImageNet 64x64 and LSUN 256x256.

Related papers

• One-Step Diffusion Distillation through Score Implicit Matching [74.91234358410281]
  We present Score Implicit Matching (SIM) a new approach to distilling pre-trained diffusion models into single-step generator models. SIM shows strong empirical performances for one-step generators. By applying SIM to a leading transformer-based diffusion model, we distill a single-step generator for text-to-image generation.
  arXiv  Detail & Related papers  (2024-10-22T08:17:20Z)
• 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)
• Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation [52.509092010267665]
  We introduce LlamaGen, a new family of image generation models that apply original next-token prediction'' paradigm of large language models to visual generation domain. It is an affirmative answer to whether vanilla autoregressive models, e.g., Llama, without inductive biases on visual signals can achieve state-of-the-art image generation performance if scaling properly.
  arXiv  Detail & Related papers  (2024-06-10T17:59:52Z)
• Multistep Distillation of Diffusion Models via Moment Matching [29.235113968156433]
  We present a new method for making diffusion models faster to sample. The method distills many-step diffusion models into few-step models by matching conditional expectations of the clean data. We obtain new state-of-the-art results on the Imagenet dataset.
  arXiv  Detail & Related papers  (2024-06-06T14:20:21Z)
• Directly Denoising Diffusion Models [6.109141407163027]
  We present Directly Denoising Diffusion Model (DDDM), a simple and generic approach for generating realistic images with few-step sampling. Our model achieves FID scores of 2.57 and 2.33 on CIFAR-10 in one-step and two-step sampling respectively, surpassing those obtained from GANs and distillation-based models. For ImageNet 64x64, our approach stands as a competitive contender against leading models.
  arXiv  Detail & Related papers  (2024-05-22T11:20:32Z)
• Multistep Consistency Models [24.443707181138553]
  A 1-step consistency model is a conventional consistency model whereas a $infty$-step consistency model is a diffusion model. By increasing the sample budget from a single step to 2-8 steps, we can train models more easily that generate higher quality samples. We show that our method scales to a text-to-image diffusion model, generating samples that are close to the quality of the original model.
  arXiv  Detail & Related papers  (2024-03-11T15:26:34Z)
• On Distillation of Guided Diffusion Models [94.95228078141626]
  We propose an approach to distilling classifier-free guided diffusion models into models that are fast to sample from. For standard diffusion models trained on the pixelspace, our approach is able to generate images visually comparable to that of the original model. For diffusion models trained on the latent-space (e.g., Stable Diffusion), our approach is able to generate high-fidelity images using as few as 1 to 4 denoising steps.
  arXiv  Detail & Related papers  (2022-10-06T18:03:56Z)
• Improved Techniques for Training Score-Based Generative Models [104.20217659157701]
  We provide a new theoretical analysis of learning and sampling from score models in high dimensional spaces. We can effortlessly scale score-based generative models to images with unprecedented resolutions. Our score-based models can generate high-fidelity samples that rival best-in-class GANs on various image datasets.
  arXiv  Detail & Related papers  (2020-06-16T09:17:17Z)

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.