Related papers: SplitFlux: Learning to Decouple Content and Style …
Recent advances in diffusion models and parameter-efficient fine-tuning (PEFT) have made text-to-image generation and customization widely accessible, with Low Rank Adaptation (LoRA) able to replicate an artist's style or subject using…
Disentanglement learning is crucial for obtaining disentangled representations and controllable generation. Current disentanglement methods face several inherent limitations: difficulty with high-resolution images, primarily focusing on…
Vision-language models like CLIP excel at recognizing the single, prominent object in a scene. However, they struggle in complex scenes containing multiple objects. We identify a fundamental reason for this limitation: VLM feature space…
Recent years have witnessed significant advancements in text-guided style transfer, primarily attributed to innovations in diffusion models. These models excel in conditional guidance, utilizing text or images to direct the sampling…
Reinforcement learning (RL) has become the core post-training technique for large language models (LLMs). RL for LLMs involves two stages: generation and training. The LLM first generates samples online, which are then used to derive…
Generative models can generate photorealistic images at scale. This raises urgent concerns about the ability to detect synthetically generated images and attribute these images to specific sources. While watermarking has emerged as a…
Existing methods for AI-generated artworks still struggle with generating high-quality stylized content, where high-level semantics are preserved, or separating fine-grained styles from various artists. We propose a novel Generative…
This work focuses on generating high-quality images with specific style of reference images and content of provided textual descriptions. Current leading algorithms, i.e., DreamBooth and LoRA, require fine-tuning for each style, leading to…
In this pioneering study, we introduce StyleWallfacer, a groundbreaking unified training and inference framework, which not only addresses various issues encountered in the style transfer process of traditional methods but also unifies the…
We introduce a method to generate 3D scenes that are disentangled into their component objects. This disentanglement is unsupervised, relying only on the knowledge of a large pretrained text-to-image model. Our key insight is that objects…
Learning disentangled representations of natural language is essential for many NLP tasks, e.g., conditional text generation, style transfer, personalized dialogue systems, etc. Similar problems have been studied extensively for other forms…
Customized image editing aims to equip pre-trained diffusion models with specific visual effects using limited paired data, typically via Low-Rank Adaptation (LoRA). As the number of desired effects grows, storing and dynamically loading…
Deep learning-based image generation has seen significant advancements with diffusion models, notably improving the quality of generated images. Despite these developments, generating images with unseen characteristics beneficial for…
Recent diffusion model customization has shown impressive results in incorporating subject or style concepts with a handful of images. However, the modular composition of multiple concepts into a customized model, aimed to efficiently merge…
In modern social networks, existing style transfer methods suffer from a serious content leakage issue, which hampers the ability to achieve serial and reversible stylization, thereby hindering the further propagation of stylized images in…
The rapid development of generative diffusion models has significantly advanced the field of style transfer. However, most current style transfer methods based on diffusion models typically involve a slow iterative optimization process,…
FLUX.1 is a diffusion-based text-to-image generation model developed by Black Forest Labs, designed to achieve faithful text-image alignment while maintaining high image quality and diversity. FLUX is considered state-of-the-art in…
Fine-tuning large language models (LLMs) on private, on-device data can empower tailored personalized AI agents. However, fine-tuning LLMs on resource-constrained edge devices faces significant challenges, including excessive computation…
Parameter-efficient fine-tuning enables fast personalization of text-to-image diffusion models, but composing multiple custom concepts remains challenging due to representation interference. Existing modular methods either rely on expensive…
Stylization for visual content aims to add specific style patterns at the pixel level while preserving the original structural features. Compared with using predefined styles, stylization guided by reference style images is more…