X-Adapter: Adding Universal Compatibility of Plugins for Upgraded Diffusion Model

TL;DR

X-Adapter is a universal module that enables existing plugins to work seamlessly with upgraded diffusion models without retraining, by controlling the model with new data and bridging different model versions.

Contribution

It introduces a novel training and alignment strategy allowing plug-and-play modules to be compatible with upgraded diffusion models without retraining.

Findings

X-Adapter achieves universal plugin compatibility.

It enables plugins of different versions to work together.

Experimental results confirm effectiveness in various scenarios.

Abstract

We introduce X-Adapter, a universal upgrader to enable the pretrained plug-and-play modules (e.g., ControlNet, LoRA) to work directly with the upgraded text-to-image diffusion model (e.g., SDXL) without further retraining. We achieve this goal by training an additional network to control the frozen upgraded model with the new text-image data pairs. In detail, X-Adapter keeps a frozen copy of the old model to preserve the connectors of different plugins. Additionally, X-Adapter adds trainable mapping layers that bridge the decoders from models of different versions for feature remapping. The remapped features will be used as guidance for the upgraded model. To enhance the guidance ability of X-Adapter, we employ a null-text training strategy for the upgraded model. After training, we also introduce a two-stage denoising strategy to align the initial latents of X-Adapter and the upgraded model. Thanks to our strategies, X-Adapter demonstrates universal compatibility with various plugins and also enables plugins of different versions to work together, thereby expanding the functionalities of diffusion community. To verify the effectiveness of the proposed method, we conduct extensive experiments and the results show that X-Adapter may facilitate wider application in the upgraded foundational diffusion model.