Year: 2025
Type: preprint
Abstract: Current sampling mechanisms for conditional diffusion models rely mainly on Classifier Free Guidance (CFG) to generate high-quality images. However, CFG requires several denoising passes in each time step, e.g., up to three passes in image editing tasks, resulting in excessive computational costs. This paper introduces a novel conditioning technique to ease the computational burden of the well-established guidance techniques, thereby significantly improving the inference time of diffusion models. We present Explicit Conditioning (EC) of the noise distribution on the input modalities to achieve this. Intuitively, we model the noise to guide the conditional diffusion model during the diffusion process. We present evaluations on image editing tasks and demonstrate that EC outperforms CFG in generating diverse high-quality images with significantly reduced computations.
Source: arXiv (Cornell University)
Authors: Noroozi, Mehdi, Ramos, Alberto Gil, Morreale, Luca, Chavhan, Ruchika, Chadwick, Malcolm, Mehrotra, Abhinav, Bhattacharya, Sourav
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6891879186
Cites:
Cited by:
Related to: