Related papers: OUSAC: Optimized Guidance Scheduling with Adaptive…

Diffusion Transformers (DiTs) have demonstrated remarkable generative capabilities, particularly benefiting from Transformer architectures that enhance visual and artistic fidelity. However, their inherently sequential denoising process…

In this paper, we propose Tortoise and Hare Guidance (THG), a training-free strategy that accelerates diffusion sampling while maintaining high-fidelity generation. We demonstrate that the noise estimate and the additional guidance term…

Generative posterior sampling using diffusion models has emerged as a dominant paradigm for solving inverse problems in imaging, which usually consists of three main components: data consistency (DC) guidance, classifier-free guidance (CFG)…

The design of diffusion-based audio generation systems has been investigated from diverse perspectives, such as data space, network architecture, and conditioning techniques, while most of these innovations require model re-training. In…

Classifier-free guidance (CFG) has emerged as a pivotal advancement in text-to-image latent diffusion models, establishing itself as a cornerstone technique for achieving high-quality image synthesis. However, under high guidance weights,…

The growing adoption of generative AI in real-world applications has exposed a critical bottleneck in the computational demands of diffusion-based text-to-image models. In this work, we propose KDC-Diff, a novel and scalable generative…

We show that diffusion models can achieve image sample quality superior to the current state-of-the-art generative models. We achieve this on unconditional image synthesis by finding a better architecture through a series of ablations. For…

Diffusion models are cutting-edge generative models adept at producing diverse, high-quality images. Despite their effectiveness, these models often require significant computational resources owing to their numerous sequential denoising…

Training-free control over editing intensity is a critical requirement for diffusion-based image editing models built on the Diffusion Transformer (DiT) architecture. Existing attention manipulation methods focus exclusively on the Key…

Enhancing the efficiency of high-quality image generation using Diffusion Models (DMs) is a significant challenge due to the iterative nature of the process. Flow Matching (FM) is emerging as a powerful generative modeling paradigm based on…

Continuous normalizing flows (CNFs) and diffusion models (DMs) generate high-quality data from a noise distribution. However, their sampling process demands multiple iterations to solve an ordinary differential equation (ODE) with high…

We introduce StreamDiffusion, a real-time diffusion pipeline designed for interactive image generation. Existing diffusion models are adept at creating images from text or image prompts, yet they often fall short in real-time interaction.…

Negative guidance -- explicitly suppressing unwanted attributes -- remains a fundamental challenge in diffusion models, particularly in few-step sampling regimes. While Classifier-Free Guidance (CFG) works well in standard settings, it…

Training-free acceleration has emerged as an advanced research area in video generation based on diffusion models. The redundancy of latents in diffusion model inference provides a natural entry point for acceleration. In this paper, we…

Diffusion Transformers (DiTs) achieve strong visual quality, but their iterative denoising process requires many costly Transformer evaluations. Training-free acceleration methods reduce this cost by caching, forecasting, or verifying…

Diffusion models excel at modeling complex and multimodal trajectory distributions for decision-making and control. Reward-gradient guided denoising has been recently proposed to generate trajectories that maximize both a differentiable…

In continual instruction tuning (CIT) scenarios, where new instruction tuning data continuously arrive in an online streaming manner, training delays from large-scale data significantly hinder real-time adaptation. Data selection can…

Existing cache-based acceleration methods for video diffusion models primarily skip early or mid denoising steps, which often leads to structural discrepancies relative to full-timestep generation and can hinder instruction following and…

Diffusion models often exhibit inconsistent sample quality due to stochastic variations inherent in their sampling trajectories. Although training-based fine-tuning (e.g. DDPO [1]) and inference-time alignment techniques[2] aim to improve…

Guidance techniques are simple yet effective for improving conditional generation in diffusion models. Albeit their empirical success, the practical implementation of guidance diverges significantly from its theoretical motivation. In this…