Related papers: When Pretty Isn't Useful: Investigating Why Modern…
Training medical AI algorithms requires large volumes of accurately labeled datasets, which are difficult to obtain in the real world. Synthetic images generated from deep generative models can help alleviate the data scarcity problem, but…
Text-to-image diffusion models have achieved widespread popularity due to their unprecedented image generation capability. In particular, their ability to synthesize and modify human faces has spurred research into using generated face…
The issue of generative pretraining for vision models has persisted as a long-standing conundrum. At present, the text-to-image (T2I) diffusion model demonstrates remarkable proficiency in generating high-definition images matching textual…
Text-to-image (T2I) diffusion models (DMs) have shown promise in generating high-quality images from textual descriptions. The real-world applications of these models require particular attention to their safety and fidelity, but this has…
Continual post-training adapts a single text-to-image diffusion model to learn new tasks without incurring the cost of separate models, but naive post-training causes forgetting of pretrained knowledge and undermines zero-shot…
Generating images from textual descriptions has recently attracted a lot of interest. While current models can generate photo-realistic images of individual objects such as birds and human faces, synthesising images with multiple objects is…
Recent text-to-image (T2I) generation models have achieved remarkable sucess by training on billion-scale datasets, following a `bigger is better' paradigm that prioritizes data quantity over availability (closed vs open source) and…
Text-to-image synthesis (T2I) aims to generate photo-realistic images which are semantically consistent with the text descriptions. Existing methods are usually built upon conditional generative adversarial networks (GANs) and initialize an…
Text-to-video (T2V) generation technology holds potential to transform multiple domains such as education, marketing, entertainment, and assistive technologies for individuals with visual or reading comprehension challenges, by creating…
With the advance of generative AI, the text-to-image (T2I) model has the ability to generate various contents. However, the generated contents cannot be fully controlled. There is a potential risk that T2I model can generate unsafe images…
Large-scale diffusion models have achieved state-of-the-art results on text-to-image synthesis (T2I) tasks. Despite their ability to generate high-quality yet creative images, we observe that attribution-binding and compositional…
Despite their impressive capabilities, diffusion-based text-to-image (T2I) models can lack faithfulness to the text prompt, where generated images may not contain all the mentioned objects, attributes or relations. To alleviate these…
During pre-training, the Text-to-Image (T2I) diffusion models encode factual knowledge into their parameters. These parameterized facts enable realistic image generation, but they may become obsolete over time, thereby misrepresenting the…
Text-to-image (T2I) generation has seen significant progress with diffusion models, enabling generation of photo-realistic images from text prompts. Despite this progress, existing methods still face challenges in following complex text…
Text-to-Image (T2I) models have transformed visual content creation, producing highly realistic images from natural language prompts. However, concerns persist around their potential to replicate and magnify existing societal biases. To…
Recent text-to-image (T2I) diffusion and flow-matching models can produce highly realistic images from natural language prompts. In practical scenarios, T2I systems are often run in a ``generate--then--select'' mode: many seeds are sampled…
Text-to-Image (T2I) diffusion/flow models have recently achieved remarkable progress in visual fidelity and text alignment. However, they remain limited when users need to precisely control image layouts, something that natural language…
Text to image generation methods (T2I) are widely popular in generating art and other creative artifacts. While visual hallucinations can be a positive factor in scenarios where creativity is appreciated, such artifacts are poorly suited…
In this paper we present and validate a new synthetic dataset for training visual entailment models. Existing datasets for visual entailment are small and sparse compared to datasets for textual entailment. Manually creating datasets is…
Recent significant advances in text-to-image models unlock the possibility of training vision systems using synthetic images, potentially overcoming the difficulty of collecting curated data at scale. It is unclear, however, how these…