Related papers: A Training-Free Style-aligned Image Generation wit…

Controllable generation, which enables fine-grained control over generated outputs, has emerged as a critical focus in visual generative models. Currently, there are two primary technical approaches in visual generation: diffusion models…

Text-to-image diffusion models have demonstrated an impressive ability to produce high-quality outputs. However, they often struggle to accurately follow fine-grained spatial information in an input text. To this end, we propose a…

Unconditional video generation is a challenging task that involves synthesizing high-quality videos that are both coherent and of extended duration. To address this challenge, researchers have used pretrained StyleGAN image generators for…

When humans read a specific text, they often visualize the corresponding images, and we hope that computers can do the same. Text-to-image synthesis (T2I), which focuses on generating high-quality images from textual descriptions, has…

We present an automated way to evaluate the text alignment of text-to-image generative diffusion models using standard image-text recognition datasets. Our method, called SelfEval, uses the generative model to compute the likelihood of real…

Diffusion models have shown great promise in text-guided image style transfer, but there is a trade-off between style transformation and content preservation due to their stochastic nature. Existing methods require computationally expensive…

The current large auto-regressive models can generate high-quality, high-resolution images, but these models require hundreds or even thousands of steps of next-token prediction during inference, resulting in substantial time consumption.…

Recent text-to-image (T2I) diffusion models have achieved remarkable advancement, yet faithfully following complex textual descriptions remains challenging due to insufficient interactions between textual and visual features. Prior…

Text-to-image (T2I) generation has advanced rapidly, making reliable evaluation critical as performance differences between models narrow. Existing evaluation practices typically apply uniform annotation mechanisms, such as Likert-scale or…

While diffusion models have shown great success in image generation, their noise-inverting generative process does not explicitly consider the structure of images, such as their inherent multi-scale nature. Inspired by diffusion models and…

Text-to-image (T2I) generative diffusion models have demonstrated outstanding performance in synthesizing diverse, high-quality visuals from text captions. Several layout-to-image models have been developed to control the generation process…

Despite recent significant strides achieved by diffusion-based Text-to-Image (T2I) models, current systems are still less capable of ensuring decent compositional generation aligned with text prompts, particularly for the multi-object…

Transformer is eminently suitable for auto-regressive image synthesis which predicts discrete value from the past values recursively to make up full image. Especially, combined with vector quantised latent representation, the…

Numerous efforts have been made to extend the ``next token prediction'' paradigm to visual contents, aiming to create a unified approach for both image generation and understanding. Nevertheless, attempts to generate images through…

Styled Handwritten Text Generation (HTG) has recently received attention from the computer vision and document analysis communities, which have developed several solutions, either GAN- or diffusion-based, that achieved promising results.…

Concept-based Explainable Artificial Intelligence (XAI) interprets deep learning models using human-understandable visual features (e.g., textures or object parts) by linking internal representations to class predictions, thereby bridging…

Text-to-image (T2I) diffusion models are popular for introducing image manipulation methods, such as editing, image fusion, inpainting, etc. At the same time, image-to-video (I2V) and text-to-video (T2V) models are also built on top of T2I…

Text-driven style transfer aims to merge the style of a reference image with content described by a text prompt. Recent advancements in text-to-image models have improved the nuance of style transformations, yet significant challenges…

Existing text-to-image diffusion models struggle to synthesize realistic images given dense captions, where each text prompt provides a detailed description for a specific image region. To address this, we propose DenseDiffusion, a…

We present Infinity, a Bitwise Visual AutoRegressive Modeling capable of generating high-resolution, photorealistic images following language instruction. Infinity redefines visual autoregressive model under a bitwise token prediction…