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 …

In this paper, we present an open-set object detector, called Grounding DINO, by marrying
Transformer-based detector DINO with grounded pre-training, which can detect arbitrary …

The incredible generative ability of large-scale text-to-image (T2I) models has demonstrated
strong power of learning complex structures and meaningful semantics. However, relying …

We present X-Decoder, a generalized decoding model that can predict pixel-level
segmentation and language tokens seamlessly. X-Decoder takes as input two types of …

We present DreamBooth3D, an approach to personalize text-to-3D generative models from
as few as 3-6 casually captured images of a subject. Our approach combines recent …

Recent advances in personalized image generation have enabled pre-trained text-to-image
models to learn new concepts from specific image sets. However these methods often …

Diffusion-based methods can generate realistic images and videos, but they struggle to edit
existing objects in a video while preserving their geometry over time. This prevents diffusion …

Neural compression is the application of neural networks and other machine learning
methods to data compression. Recent advances in statistical machine learning have opened …

Recent large-scale generative models learned on big data are capable of synthesizing
incredible images yet suffer from limited controllability. This work offers a new generation …

Recent text-to-image diffusion models have demonstrated an astonishing capacity to
generate high-quality images. However, researchers mainly studied the way of synthesizing …