Related papers: Autoregressive Styled Text Image Generation, but M…
Recent advancements in autoregressive and diffusion models have led to strong performance in image generation with short scene text words. However, generating coherent, long-form text in images, such as paragraphs in slides or documents,…
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…
Recently, the multimedia community has witnessed the rise of diffusion models trained on large-scale multi-modal data for visual content creation, particularly in the field of text-to-image generation. In this paper, we propose a new task…
Autoregressive models have been widely used in unsupervised text style transfer. Despite their success, these models still suffer from the content preservation problem that they usually ignore part of the source sentence and generate some…
Watermarking the outputs of generative models has emerged as a promising approach for tracking their provenance. Despite significant interest in autoregressive image generation models and their potential for misuse, no prior work has…
Autoregressive generative models of images tend to be biased towards capturing local structure, and as a result they often produce samples which are lacking in terms of large-scale coherence. To address this, we propose two methods to learn…
While image generation techniques are now capable of producing high-quality images that respect prompts which span multiple sentences, the task of text-guided image editing remains a challenge. Even edit requests that consist of only a few…
In this work, we first revisit the sampling issues in current autoregressive (AR) image generation models and identify that image tokens, unlike text tokens, exhibit lower information density and non-uniform spatial distribution.…
Conditional text-to-image generation is an active area of research, with many possible applications. Existing research has primarily focused on generating a single image from available conditioning information in one step. One practical…
Prompting approaches have been recently explored in text style transfer, where a textual prompt is used to query a pretrained language model to generate style-transferred texts word by word in an autoregressive manner. However, such a…
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…
Generating synthetic images of handwritten text in a writer-specific style is a challenging task, especially in the case of unseen styles and new words, and even more when these latter contain characters that are rarely encountered during…
Text style transfer is the task of transferring the style of text having certain stylistic attributes, while preserving non-stylistic or content information. In this work we introduce the Generative Style Transformer (GST) - a new approach…
While recent text-to-image models can generate photorealistic images from text prompts that reflect detailed instructions, they still face significant challenges in accurately rendering words in the image. In this paper, we propose to…
Generating high-quality and diverse human images is an important yet challenging task in vision and graphics. However, existing generative models often fall short under the high diversity of clothing shapes and textures. Furthermore, the…
Personalized text-to-image models allow users to generate varied styles of images (specified with a sentence) for an object (specified with a set of reference images). While remarkable results have been achieved using diffusion-based…
Author stylized rewriting is the task of rewriting an input text in a particular author's style. Recent works in this area have leveraged Transformer-based language models in a denoising autoencoder setup to generate author stylized text…
Autoregressive models have demonstrated great performance in natural language processing (NLP) with impressive scalability, adaptability and generalizability. Inspired by their notable success in NLP field, autoregressive models have been…
We develop an approach for text-to-image generation that embraces additional retrieval images, driven by a combination of implicit visual guidance loss and generative objectives. Unlike most existing text-to-image generation methods which…
Although significant progress has been made in many tasks within the field of Natural Language Processing (NLP), Controlled Text Generation (CTG) continues to face numerous challenges, particularly in achieving fine-grained conditional…