Related papers: Resolving the Identity Crisis in Text-to-Image Gen…

Text-to-image (T2I) models have significantly advanced the development of artificial intelligence, enabling the generation of high-quality images in diverse contexts based on specific text prompts. However, existing T2I-based methods often…

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…

Large Language Models (LLMs) are increasingly aligned with human preferences through Reinforcement Learning from Human Feedback (RLHF). Among RLHF methods, Group Relative Policy Optimization (GRPO) has gained attention for its simplicity…

Reinforcement learning (RL) has garnered increasing attention in text-to-image (T2I) generation. However, most existing RL approaches are tailored to either diffusion models or autoregressive models, overlooking an important alternative:…

The current text-to-video (T2V) generation has made significant progress in synthesizing realistic general videos, but it is still under-explored in identity-specific human video generation with customized ID images. The key challenge lies…

In this paper, we present an end-to-end approach to generate high-resolution person images conditioned on texts only. State-of-the-art text-to-image generation models are mainly designed for center-object generation, e.g., flowers and…

Multi-subject personalized image generation aims to synthesize customized images containing multiple specified subjects without requiring test-time optimization. However, achieving fine-grained independent control over multiple subjects…

Subject-driven image generation models face a fundamental trade-off between identity preservation (fidelity) and prompt adherence (editability). While online reinforcement learning (RL), specifically GPRO, offers a promising solution, we…

Multi-subject image generation requires seamlessly harmonizing multiple reference identities within a coherent scene. However, existing methods relying on rigid spatial masks or localized attention often struggle with the…

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…

Text-to-image (T2I) diffusion models are effective at producing semantically aligned images, but their reliance on training data distributions limits their ability to synthesize truly novel, out-of-distribution concepts. Existing methods…

In video Multimodal Large Language Models (video MLLMs), the visual encapsulation process plays a pivotal role in converting video contents into representative tokens for LLM input. While linear projectors are widely employed for…

Image diversity remains a fundamental challenge for text-to-image diffusion models. Low-diversity models tend to generate repetitive outputs, increasing sampling redundancy and hindering both creative exploration and downstream…

Employing clustering strategy to assign unlabeled target images with pseudo labels has become a trend for person re-identification (re-ID) algorithms in domain adaptation. A potential limitation of these clustering-based methods is that…

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…

Recent advancements in image mixing and generative data augmentation have shown promise in enhancing image classification. However, these techniques face the challenge of balancing semantic fidelity with diversity. Specifically, image…

With the rise of cameras and smart sensors, humanity generates an exponential amount of data. This valuable information, including underrepresented cases like AI in medical settings, can fuel new deep-learning tools. However, data…

Identity-preserving text-to-video (IPT2V) generation aims to create high-fidelity videos with consistent human identity. It is an important task in video generation but remains an open problem for generative models. This paper pushes the…

In computer vision, it is well-known that a lack of data diversity will impair model performance. In this study, we address the challenges of enhancing the dataset diversity problem in order to benefit various downstream tasks such as…

Achieving flexible and high-fidelity identity-preserved image generation remains formidable, particularly with advanced Diffusion Transformers (DiTs) like FLUX. We introduce InfiniteYou (InfU), one of the earliest robust frameworks…