Large-scale text-to-image diffusion models have made amazing advances. However, the
status quo is to use text input alone, which can impede controllability. In this work, we …

We propose a novel Latent Diffusion Transformer, namely Latte, for video generation. Latte
first extracts spatio-temporal tokens from input videos and then adopts a series of …

Recent text-to-image generation models have demonstrated impressive capability of
generating text-aligned images with high fidelity. However, generating images of novel …

Recent works have demonstrated that using reinforcement learning (RL) with multiple
quality rewards can improve the quality of generated images in text-to-image (T2I) …

Text-to-image generation (TTI) refers to the usage of models that could process text input
and generate high fidelity images based on text descriptions. Text-to-image generation …

There is a bias in the inference pipeline of most diffusion models. This bias arises from a
signal leak whose distribution deviates from the noise distribution, creating a discrepancy …

Recent text-to-image generative models have enabled us to transform our words into
vibrant, captivating imagery. The surge of personalization techniques that has followed has …

It is well-known that image quality assessment usually meets with the problem of perception-
distortion (pd) tradeoff. The existing deep image super-resolution (SR) methods either focus …

Generative models have enabled intuitive image creation and manipulation using natural
language. In particular, diffusion models have recently shown remarkable results for natural …

Recently, there has been significant progress in the development of large models. Following
the success of ChatGPT, numerous language models have been introduced, demonstrating …