RepControlNet: ControlNet Reparameterization

TL;DR

RepControlNet introduces a reparameterization approach for diffusion models that enables controllable generation without additional computational costs, improving efficiency and performance over existing methods.

Contribution

This paper presents RepControlNet, a novel reparameterization technique that achieves controllable diffusion model generation without increasing parameters or computation.

Findings

Effective control without extra parameters

Surpasses ControlNet in efficiency and performance

Validated on SD1.5 and SDXL datasets

Abstract

With the wide application of diffusion model, the high cost of inference resources has became an important bottleneck for its universal application. Controllable generation, such as ControlNet, is one of the key research directions of diffusion model, and the research related to inference acceleration and model compression is more important. In order to solve this problem, this paper proposes a modal reparameterization method, RepControlNet, to realize the controllable generation of diffusion models without increasing computation. In the training process, RepControlNet uses the adapter to modulate the modal information into the feature space, copy the CNN and MLP learnable layers of the original diffusion model as the modal network, and initialize these weights based on the original weights and coefficients. The training process only optimizes the parameters of the modal network. In the inference process, the weights of the neutralization original diffusion model in the modal network are reparameterized, which can be compared with or even surpass the methods such as ControlNet, which use additional parameters and computational quantities, without increasing the number of parameters. We have carried out a large number of experiments on both SD1.5 and SDXL, and the experimental results show the effectiveness and efficiency of the proposed RepControlNet.