L Li, H Li, X Zheng, J Wu, X Xiao… - Proceedings of the …, 2023 - openaccess.thecvf.com
Diffusion models are emerging expressive generative models, in which a large number of time steps (inference steps) are required for a single image generation. To accelerate such …
Z Zhou, D Chen, C Wang… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Sampling from diffusion models can be treated as solving the corresponding ordinary differential equations (ODEs) with the aim of obtaining an accurate solution with as few …
Denoising diffusion models (DDMs) have emerged as a powerful class of generative models. A forward diffusion process slowly perturbs the data, while a deep model learns to …
Denoising diffusion models have been a mainstream approach for image generation, however, training these models often suffers from slow convergence. In this paper, we …
Diffusion models have demonstrated remarkable progress in image generation quality, especially when guidance is used to control the generative process. However, guidance …
Abstract Denoising Diffusion Probabilistic Model (DDPM) is able to make flexible conditional image generation from prior noise to real data, by introducing an independent noise-aware …
JN Yan, J Gu, AM Rush - … of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
In recent advancements in high-fidelity image generation Denoising Diffusion Probabilistic Models (DDPMs) have emerged as a key player. However their application at high …
Denoising diffusion (score-based) generative models have recently achieved significant accomplishments in generating realistic and diverse data. These approaches define a …
We consider guiding denoising diffusion models with general differentiable loss functions in a plug-and-play fashion, enabling controllable generation without additional training. This …