DivControl: Knowledge Diversion for Controllable Image Generation
By: Yucheng Xie , Fu Feng , Ruixiao Shi and more
Potential Business Impact:
Makes AI draw pictures from many different ideas.
Diffusion models have advanced from text-to-image (T2I) to image-to-image (I2I) generation by incorporating structured inputs such as depth maps, enabling fine-grained spatial control. However, existing methods either train separate models for each condition or rely on unified architectures with entangled representations, resulting in poor generalization and high adaptation costs for novel conditions. To this end, we propose DivControl, a decomposable pretraining framework for unified controllable generation and efficient adaptation. DivControl factorizes ControlNet via SVD into basic components-pairs of singular vectors-which are disentangled into condition-agnostic learngenes and condition-specific tailors through knowledge diversion during multi-condition training. Knowledge diversion is implemented via a dynamic gate that performs soft routing over tailors based on the semantics of condition instructions, enabling zero-shot generalization and parameter-efficient adaptation to novel conditions. To further improve condition fidelity and training efficiency, we introduce a representation alignment loss that aligns condition embeddings with early diffusion features. Extensive experiments demonstrate that DivControl achieves state-of-the-art controllability with 36.4$\times$ less training cost, while simultaneously improving average performance on basic conditions. It also delivers strong zero-shot and few-shot performance on unseen conditions, demonstrating superior scalability, modularity, and transferability.
Similar Papers
Knowledge Diversion for Efficient Morphology Control and Policy Transfer
Machine Learning (CS)
Robots learn new tasks faster, using less computer power.
CtrlVDiff: Controllable Video Generation via Unified Multimodal Video Diffusion
CV and Pattern Recognition
Makes videos change appearance and content easily.
EVCtrl: Efficient Control Adapter for Visual Generation
CV and Pattern Recognition
Makes AI create pictures and videos faster.