Related papers: LooseRoPE: Content-aware Attention Manipulation fo…
Positional encodings are essential to transformer-based generative models, yet their behavior in multimodal and attention-sharing settings is not fully understood. In this work, we present a principled analysis of Rotary Positional…
Diffusion models (DMs) have gained prominence due to their ability to generate high-quality varied images with recent advancements in text-to-image generation. The research focus is now shifting towards the controllability of DMs. A…
Recent developments in the field of diffusion models have demonstrated an exceptional capacity to generate high-quality prompt-conditioned image edits. Nevertheless, previous approaches have primarily relied on textual prompts for image…
We present a novel, training-free approach for textual editing of real images using diffusion models. Unlike prior methods that rely on computationally expensive finetuning, our approach leverages LAtent SPatial Alignment (LASPA) to…
Video generation with controllable camera viewpoints is essential for applications such as interactive content creation, gaming, and simulation. Existing methods typically adapt pre-trained video models using camera poses relative to a…
Transformers rely on explicit positional encoding to model structure in data. While Rotary Position Embedding (RoPE) excels in 1D domains, its application to image generation reveals significant limitations such as fine-grained spatial…
Positional encoding is essential for large language models (LLMs) to represent sequence order, yet recent studies show that Rotary Position Embedding (RoPE) can induce massive activation. We investigate the source of these instabilities via…
Text-driven image editing enables users to flexibly modify visual content through natural language instructions, and is widely applied to tasks such as semantic object replacement, insertion, and removal. While recent inversion-based…
Diffusion Magnetic Resonance Imaging (dMRI) plays a critical role in studying microstructural changes in the brain. It is, therefore, widely used in clinical practice; yet progress in learning general-purpose representations from dMRI has…
Precise spatial control in diffusion-based style transfer remains challenging. This challenge arises because diffusion models treat style as a global feature and lack explicit spatial grounding of style representations, making it difficult…
Positional encoding is a vital component of Transformer architectures, enabling models to incorporate sequence order into self-attention mechanisms. Rotary Positional Embeddings (RoPE) have become a widely adopted solution due to their…
Recent diffusion-based generators can produce high-quality images from textual prompts. However, they often disregard textual instructions that specify the spatial layout of the composition. We propose a simple approach that achieves robust…
Diffusion-based Image Editing has achieved significant success in recent years. However, it remains challenging to achieve high-quality image editing while maintaining the background similarity without sacrificing speed or memory…
Text-to-image synthesis has achieved high-quality results with recent advances in diffusion models. However, text input alone has high spatial ambiguity and limited user controllability. Most existing methods allow spatial control through…
We seek to give users precise control over diffusion-based image generation by modeling complex scenes as sequences of layers, which define the desired spatial arrangement and visual attributes of objects in the scene. Collage Diffusion…
Text-to-image diffusion models have proven effective for solving many image editing tasks. However, the seemingly straightforward task of seamlessly relocating objects within a scene remains surprisingly challenging. Existing methods…
Rotary Position Embedding (RoPE) has shown strong performance in text-based Large Language Models (LLMs), but extending it to video remains a challenge due to the intricate spatiotemporal structure of video frames. Existing adaptations,…
A precise and user-friendly manipulation of image content while preserving image fidelity has always been crucial to the field of image editing. Thanks to the power of generative models, recent point-based image editing methods allow users…
We present TALE, a novel training-free framework harnessing the generative capabilities of text-to-image diffusion models to address the cross-domain image composition task that focuses on flawlessly incorporating user-specified objects…
Diffusion models generate images with an unprecedented level of quality, but how can we freely rearrange image layouts? Recent works generate controllable scenes via learning spatially disentangled latent codes, but these methods do not…