Related papers: Q&C: When Quantization Meets Cache in Efficient Im…

Diffusion transformers have demonstrated remarkable capabilities in generating videos. However, their practical deployment is severely constrained by high memory usage and computational cost. Post-Training Quantization provides a practical…

Although Diffusion Transformer (DiT) has emerged as a predominant architecture for image and video generation, its iterative denoising process results in slow inference, which hinders broader applicability and development. Caching-based…

Diffusion Transformers (DiTs) have achieved impressive performance in text-to-image and text-to-video generation. However, their high computational cost and large parameter sizes pose significant challenges for usage in resource-constrained…

Diffusion models have emerged as preeminent contenders in the realm of generative models. Distinguished by their distinctive sequential generative processes, characterized by hundreds or even thousands of timesteps, diffusion models…

Text-to-image generation via Stable Diffusion models (SDM) have demonstrated remarkable capabilities. However, their computational intensity, particularly in the iterative denoising process, hinders real-time deployment in latency-sensitive…

Recent years have witnessed the rapid development of acceleration techniques for diffusion models, especially caching-based acceleration methods. These studies seek to answer two fundamental questions: "When to cache" and "How to use…

Diffusion models have been widely adopted in image and video generation. However, their complex network architecture leads to high inference overhead for its generation process. Existing diffusion quantization methods primarily focus on the…

Recent success of large text-to-image models has empirically underscored the exceptional performance of diffusion models in generative tasks. To facilitate their efficient deployment on resource-constrained edge devices, model quantization…

Diffusion-based video editing has emerged as an important paradigm for high-quality and flexible content generation. However, despite their generality and strong modeling capacity, Diffusion Transformers (DiT) remain computationally…

Model quantization is a promising method for accelerating and compressing diffusion models. Nevertheless, since post-training quantization (PTQ) fails catastrophically at low-bit cases, quantization-aware training (QAT) is essential.…

Diffusion Transformers require repeated denoiser evaluations during iterative sampling, making inference computationally expensive. Cache-based acceleration reduces this cost by reusing intermediate representations across denoising steps,…

Diffusion models deliver high-fidelity synthesis but remain slow due to iterative sampling. We empirically observe there exists feature invariance in deterministic sampling, and present InvarDiff, a training-free acceleration method that…

Diffusion models have revolutionized generative tasks, especially in the domain of text-to-image synthesis; however, their iterative denoising process demands substantial computational resources. In this paper, we present a novel…

Diffusion Transformers (DiTs) have recently gained substantial attention in both industrial and academic fields for their superior visual generation capabilities, outperforming traditional diffusion models that use U-Net. However,the…

In this paper, we uncover the hidden potential of Diffusion Transformers (DiTs) to significantly enhance generative tasks. Through an in-depth analysis of the denoising process, we demonstrate that introducing a single learned scaling…

Diffusion Transformers (DiTs) achieve superior image generation quality but suffer from quadratic computational complexity relative to token count. While various token reduction (TR) methods have been proposed to mitigate this cost, they…

Diffusion models achieve superior performance in image generation tasks. However, it incurs significant computation overheads due to its iterative structure. To address these overheads, we analyze this iterative structure and observe that…

Diffusion models have achieved great success in image synthesis through iterative noise estimation using deep neural networks. However, the slow inference, high memory consumption, and computation intensity of the noise estimation model…

Deep learning has made remarkable progress recently, largely due to the availability of large, well-labeled datasets. However, the training on such datasets elevates costs and computational demands. To address this, various techniques like…

Diffusion models have achieved remarkable progress in high-fidelity image, video, and audio generation, yet inference remains computationally expensive. Nevertheless, current diffusion acceleration methods based on distributed parallelism…