Related papers: Improving Compositional Attribute Binding in Text-…
Can continuous diffusion models bring the same performance breakthrough on natural language they did for image generation? To circumvent the discrete nature of text data, we can simply project tokens in a continuous space of embeddings, as…
Image-text contrastive models like CLIP have wide applications in zero-shot classification, image-text retrieval, and transfer learning. However, they often struggle on compositional visio-linguistic tasks (e.g., attribute-binding or…
Image composition has advanced significantly with large-scale pre-trained T2I diffusion models. Despite progress in same-domain composition, cross-domain composition remains under-explored. The main challenges are the stochastic nature of…
Image-text representation learning forms a cornerstone in vision-language models, where pairs of images and textual descriptions are contrastively aligned in a shared embedding space. Since visual and textual concepts are naturally…
Generating high-fidelity images of humans with fine-grained control over attributes such as hairstyle and clothing remains a core challenge in personalized text-to-image synthesis. While prior methods emphasize identity preservation from a…
Diffusion models excel at text-to-image generation, especially in subject-driven generation for personalized images. However, existing methods are inefficient due to the subject-specific fine-tuning, which is computationally intensive and…
Deep learning models can encounter unexpected failures, especially when dealing with challenging sub-populations. One common reason for these failures is the occurrence of objects in backgrounds that are rarely seen during training. To gain…
A fundamental aspect of the semantics of natural language is that novel meanings can be formed from the composition of previously known parts. Vision-language models (VLMs) have made significant progress in recent years, however, there is…
The application of zero-shot learning in computer vision has been revolutionized by the use of image-text matching models. The most notable example, CLIP, has been widely used for both zero-shot classification and guiding generative models…
Text-conditioned image generation has made significant progress in recent years with generative adversarial networks and more recently, diffusion models. While diffusion models conditioned on text prompts have produced impressive and…
Text-to-image generation for personalized identities aims at incorporating the specific identity into images using a text prompt and an identity image. Based on the powerful generative capabilities of DDPMs, many previous works adopt…
Generative diffusion models offer a natural choice for data augmentation when training complex vision models. However, ensuring reliability of their generative content as augmentation samples remains an open challenge. Despite a number of…
Text-to-image diffusion models achieve impressive visual fidelity, yet they remain unreliable in multi-object generation. Despite extensive empirical evidence of these failures, the underlying causes remain unclear. We begin by asking how…
CLIP (Contrastive Language-Image Pre-Training) is a multimodal neural network trained on (text, image) pairs to predict the most relevant text caption given an image. It has been used extensively in image generation by connecting its output…
Training a text-to-image generator in the general domain (e.g., Dall.e, CogView) requires huge amounts of paired text-image data, which is too expensive to collect. In this paper, we propose a self-supervised scheme named as CLIP-GEN for…
We propose CatVersion, an inversion-based method that learns the personalized concept through a handful of examples. Subsequently, users can utilize text prompts to generate images that embody the personalized concept, thereby achieving…
Recent advances in text-to-image generators have led to substantial capabilities in image generation. However, the complexity of prompts acts as a bottleneck in the quality of images generated. A particular under-explored facet is the…
Text-to-image synthesis has made encouraging progress and attracted lots of public attention recently. However, popular evaluation metrics in this area, like the Inception Score and Fr'echet Inception Distance, incur several issues. First…
Large-scale text-to-image diffusion models have achieved great success in synthesizing high-quality and diverse images given target text prompts. Despite the revolutionary image generation ability, current state-of-the-art models still…
This work proposes aesthetic gradients, a method to personalize a CLIP-conditioned diffusion model by guiding the generative process towards custom aesthetics defined by the user from a set of images. The approach is validated with…