Adding Conditional Control to Text-to-Image Diffusion Models
This work addresses the need for enhanced control in image generation for AI and creative applications, representing a novel method for a known bottleneck rather than a foundational shift.
The authors tackled the problem of adding spatial conditioning controls to pretrained text-to-image diffusion models by introducing ControlNet, which enables diverse controls like edges and depth, and demonstrated robust training with datasets as small as under 50k images.
We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large diffusion models, and reuses their deep and robust encoding layers pretrained with billions of images as a strong backbone to learn a diverse set of conditional controls. The neural architecture is connected with "zero convolutions" (zero-initialized convolution layers) that progressively grow the parameters from zero and ensure that no harmful noise could affect the finetuning. We test various conditioning controls, eg, edges, depth, segmentation, human pose, etc, with Stable Diffusion, using single or multiple conditions, with or without prompts. We show that the training of ControlNets is robust with small (<50k) and large (>1m) datasets. Extensive results show that ControlNet may facilitate wider applications to control image diffusion models.