Related papers: Pick-and-Draw: Training-free Semantic Guidance for…

Personalized text-to-image generation using diffusion models has recently emerged and garnered significant interest. This task learns a novel concept (e.g., a unique toy), illustrated in a handful of images, into a generative model that…

While modern diffusion models excel at generating high-quality and diverse images, they still struggle with high-fidelity compositional and multimodal control, particularly when users simultaneously specify text prompts, subject references,…

A plethora of text-guided image editing methods has recently been developed by leveraging the impressive capabilities of large-scale diffusion-based generative models especially Stable Diffusion. Despite the success of diffusion models in…

Recent advances in generative modeling have enabled the generation of high-quality synthetic data that is applicable in a variety of domains, including face recognition. Here, state-of-the-art generative models typically rely on…

Recent text-to-image diffusion models can generate striking visuals from text prompts, but they often fail to maintain subject consistency across generations and contexts. One major limitation of current fine-tuning approaches is the…

Generating a coherent sequence of images that tells a visual story, using text-to-image diffusion models, often faces the critical challenge of maintaining subject consistency across all story scenes. Existing approaches, which typically…

Teaching text-to-image models to be creative involves using style ambiguity loss, which requires a pretrained classifier. In this work, we explore a new form of the style ambiguity training objective, used to approximate creativity, that…

Latent diffusion models excel at producing high-quality images from text. Yet, concerns appear about the lack of diversity in the generated imagery. To tackle this, we introduce Diverse Diffusion, a method for boosting image diversity…

Latent diffusion models (LDMs) dominate high-quality image generation, yet integrating representation learning with generative modeling remains a challenge. We introduce a novel generative image modeling framework that seamlessly bridges…

Advanced diffusion models have made notable progress in text-to-image compositional generation. However, it is still a challenge for existing models to achieve text-image alignment when confronted with complex text prompts. In this work, we…

Guidance serves as a key concept in diffusion models, yet its effectiveness is often limited by the need for extra data annotation or classifier pretraining. That is why guidance was harnessed from self-supervised learning backbones, like…

Generic image inpainting aims to complete a corrupted image by borrowing surrounding information, which barely generates novel content. By contrast, multi-modal inpainting provides more flexible and useful controls on the inpainted content,…

Many applications can benefit from personalized image generation models, including image enhancement, video conferences, just to name a few. Existing works achieved personalization by fine-tuning one model for each person. While being…

Recent breakthroughs in text-to-image diffusion models have significantly advanced the generation of high-fidelity, photo-realistic images from textual descriptions. Yet, these models often struggle with interpreting spatial arrangements…

Recently, text-to-image models based on diffusion have achieved remarkable success in generating high-quality images. However, the challenge of personalized, controllable generation of instances within these images remains an area in need…

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…

Based on recent advanced diffusion models, Text-to-image (T2I) generation models have demonstrated their capabilities to generate diverse and high-quality images. However, leveraging their potential for real-world content creation,…

Face stylization refers to the transformation of a face into a specific portrait style. However, current methods require the use of example-based adaptation approaches to fine-tune pre-trained generative models so that they demand lots of…

Although diffusion models have demonstrated remarkable generative capabilities, existing style transfer techniques often struggle to maintain identity while achieving high-quality stylization. This limitation becomes particularly critical…

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…