While generative models produce high-quality images of concepts learned from a large-
scale database, a user often wishes to synthesize instantiations of their own concepts (for …

Diffusion models are powerful, but they require a lot of time and data to train. We propose
Patch Diffusion, a generic patch-wise training framework, to significantly reduce the training …

Large-scale text-to-image diffusion models can generate high-fidelity images with powerful
compositional ability. However, these models are typically trained on an enormous amount …

Large text-to-image models achieved a remarkable leap in the evolution of AI, enabling high-
quality and diverse synthesis of images from a given text prompt. However, these models …

Customized generation using diffusion models has made impressive progress in image
generation but remains unsatisfactory in the challenging video generation task as it requires …

Can a generative model be trained to produce images from a specific domain, guided only
by a text prompt, without seeing any image? In other words: can an image generator be …

Generative Adversarial Networks (GANs) have achieved remarkable achievements in image
synthesis. These successes of GANs rely on large scale datasets, requiring too much cost …

Training generative models, such as GANs, on a target domain containing limited examples
(eg, 10) can easily result in overfitting. In this work, we seek to utilize a large source domain …

Anomaly inspection plays an important role in industrial manufacture. Existing anomaly
inspection methods are limited in their performance due to insufficient anomaly data …

Image-to-image translation (I2I) aims to transfer images from a source domain to a target
domain while preserving the content representations. I2I has drawn increasing attention and …