Related papers: Q-Sched: Pushing the Boundaries of Few-Step Diffus…
Diffusion-based text-to-image generation models trained on extensive text-image pairs have demonstrated the ability to produce photorealistic images aligned with textual descriptions. However, a significant limitation of these models is…
Deploying Vision-Language Models (VLMs) on edge devices (e.g., smartphones and robots) is crucial for enabling low-latency and privacy-preserving intelligent applications. Given the resource constraints of these devices, quantization offers…
This paper proposes a training method having multiple cyclic training for achieving enhanced performance in low-bit quantized convolutional neural networks (CNNs). Quantization is a popular method for obtaining lightweight CNNs, where the…
Recent advancements in diffusion models have positioned them at the forefront of image generation. Despite their superior performance, diffusion models are not without drawbacks; they are characterized by complex architectures and…
The recent introduction of Diffusion Transformers (DiTs) has demonstrated exceptional capabilities in image generation by using a different backbone architecture, departing from traditional U-Nets and embracing the scalable nature of…
Diffusion Transformers (DiTs) enable high-quality audio synthesis but are often computationally intensive and require substantial storage, which limits their practical deployment. In this paper, we present a comprehensive evaluation of…
Stable Diffusion has advanced text-to-image synthesis, but training models to generate images with accurate object quantity is still difficult due to the high computational cost and the challenge of teaching models the abstract concept of…
Diffusion Models (DM) have democratized AI image generation through an iterative denoising process. Quantization is a major technique to alleviate the inference cost and reduce the size of DM denoiser networks. However, as denoisers evolve…
In recent years, diffusion models have demonstrated remarkable success in high-fidelity image synthesis. However, fine-tuning these models for specialized domains, such as medical imaging, remains challenging due to limited domain-specific…
Text-to-image diffusion models often exhibit degraded performance when generating images beyond their training resolution. Recent training-free methods can mitigate this limitation, but they often require substantial computation or are…
The diffusion-based text-to-image model harbors immense potential in transferring reference style. However, current encoder-based approaches significantly impair the text controllability of text-to-image models while transferring styles. In…
We present an ultra-efficient post-training method for shortcutting large-scale pre-trained flow matching diffusion models into efficient few-step samplers, enabled by novel velocity field self-distillation. While shortcutting in flow…
Diffusion models have recently shown great promise for generative modeling, outperforming GANs on perceptual quality and autoregressive models at density estimation. A remaining downside is their slow sampling time: generating high quality…
Attention mechanism has been crucial for image diffusion models, however, their quadratic computational complexity limits the sizes of images we can process within reasonable time and memory constraints. This paper investigates the…
Quantization has become a predominant approach for model compression, enabling deployment of large models trained on GPUs onto smaller form-factor devices for inference. Quantization-aware training (QAT) optimizes model parameters with…
Most post-training methods for text-to-image samplers focus on model weights: either fine-tuning the backbone for alignment or distilling it for few-step efficiency. We take a different route: rescheduling the sampling timeline of a frozen…
Extensive pre-training with large data is indispensable for downstream geometry and semantic visual perception tasks. Thanks to large-scale text-to-image (T2I) pretraining, recent works show promising results by simply fine-tuning T2I…
Diffusion models excel at generating high-likelihood samples but often require alignment with downstream objectives. Existing fine-tuning methods for diffusion models significantly suffer from reward over-optimization, resulting in…
Quantizing deep neural networks ,reducing the precision (bit-width) of their computations, can remarkably decrease memory usage and accelerate processing, making these models more suitable for large-scale medical imaging applications with…
Text-to-image diffusion models can create stunning images from natural language descriptions that rival the work of professional artists and photographers. However, these models are large, with complex network architectures and tens of…