Condition-Aware Neural Network for Controlled Image Generation
This addresses the problem of efficient and high-quality conditional image generation for AI applications, representing a strong specific gain rather than a broad paradigm shift.
The paper tackles controlled image generation by proposing Condition-Aware Neural Network (CAN), which dynamically manipulates neural network weights based on input conditions, achieving a 2.78 FID on ImageNet 512x512 with 52x fewer MACs per step compared to DiT-XL/2.
We present Condition-Aware Neural Network (CAN), a new method for adding control to image generative models. In parallel to prior conditional control methods, CAN controls the image generation process by dynamically manipulating the weight of the neural network. This is achieved by introducing a condition-aware weight generation module that generates conditional weight for convolution/linear layers based on the input condition. We test CAN on class-conditional image generation on ImageNet and text-to-image generation on COCO. CAN consistently delivers significant improvements for diffusion transformer models, including DiT and UViT. In particular, CAN combined with EfficientViT (CaT) achieves 2.78 FID on ImageNet 512x512, surpassing DiT-XL/2 while requiring 52x fewer MACs per sampling step.