使用動量的擴散取樣以減輕發散藝術品效應

摘要

儘管擴散模型在圖像生成方面取得了顯著的成功，但緩慢的採樣仍然是一個持續存在的問題。為了加速採樣過程，先前的研究將擴散採樣重新定義為一個 ODE/SDE，並引入了高階數值方法。然而，這些方法通常會產生發散的人工瑕疵，特別是在採樣步驟較少時，這限制了可實現的加速度。在本文中，我們研究了這些瑕疵的潛在原因，並提出這些方法的小穩定區域可能是主要原因。為了解決這個問題，我們提出了兩種新技術。第一種技術涉及將 Heavy Ball（HB）動量，一種用於改善優化的眾所周知技術，納入現有的擴散數值方法中，以擴大它們的穩定區域。我們還證明了結果方法具有一階收斂。第二種技術，稱為廣義 Heavy Ball（GHVB），構建了一種新的高階方法，提供了在準確性和瑕疵抑制之間的可變折衷。實驗結果表明，我們的技術在減少瑕疵和提高圖像質量方面非常有效，在像素基礎和潛在基礎的低步採樣的擴散模型上超越了最先進的擴散求解器。我們的研究為未來擴散工作的數值方法設計提供了新的見解。

English

Despite the remarkable success of diffusion models in image generation, slow sampling remains a persistent issue. To accelerate the sampling process, prior studies have reformulated diffusion sampling as an ODE/SDE and introduced higher-order numerical methods. However, these methods often produce divergence artifacts, especially with a low number of sampling steps, which limits the achievable acceleration. In this paper, we investigate the potential causes of these artifacts and suggest that the small stability regions of these methods could be the principal cause. To address this issue, we propose two novel techniques. The first technique involves the incorporation of Heavy Ball (HB) momentum, a well-known technique for improving optimization, into existing diffusion numerical methods to expand their stability regions. We also prove that the resulting methods have first-order convergence. The second technique, called Generalized Heavy Ball (GHVB), constructs a new high-order method that offers a variable trade-off between accuracy and artifact suppression. Experimental results show that our techniques are highly effective in reducing artifacts and improving image quality, surpassing state-of-the-art diffusion solvers on both pixel-based and latent-based diffusion models for low-step sampling. Our research provides novel insights into the design of numerical methods for future diffusion work.

使用動量的擴散取樣以減輕發散藝術品效應

Diffusion Sampling with Momentum for Mitigating Divergence Artifacts

摘要

Support