Input-Adaptive Generative Dynamics in Diffusion Models

TL;DR

This paper introduces an input-adaptive approach to diffusion models, allowing the generative process to vary per sample, improving efficiency and maintaining quality in conditional image generation.

Contribution

It proposes a novel framework where diffusion trajectories adapt to individual inputs, trained under diverse conditions to enhance flexibility and efficiency.

Findings

Adaptive diffusion trajectories vary across inputs.

Generation quality is maintained despite fewer sampling steps.

The approach demonstrates improved efficiency in conditional image generation.

Abstract

Diffusion models typically generate data through a fixed denoising trajectory that is shared across all samples. However, generation targets can differ in complexity, suggesting that a single pre-defined diffusion process may not be optimal for every input. In this work, we investigate input-adaptive generative dynamics for diffusion models, where the generation process itself adapts to the conditions of each sample. Instead of relying on a fixed diffusion trajectory, the proposed framework allows the generative dynamics to adjust across inputs according to their generation requirements. To enable this behavior, we train the diffusion backbone under varying horizons and noise schedules, so that it can operate consistently under different input-adaptive trajectories. Experiments on conditional image generation show that diffusion trajectories can vary across inputs while maintaining generation quality and reducing the average number of sampling steps. These results provide a proof of the concept that diffusion processes can benefit from input-adaptive generative dynamics rather than relying on a single fixed trajectory.