Related papers: IterComp: Iterative Composition-Aware Feedback Lea…

We present BootComp, a novel framework based on text-to-image diffusion models for controllable human image generation with multiple reference garments. Here, the main bottleneck is data acquisition for training: collecting a large-scale…

Building upon Diff-A-Riff, a latent diffusion model for musical instrument accompaniment generation, we present a series of improvements targeting quality, diversity, inference speed, and text-driven control. First, we upgrade the…

Diffusion-based models have recently revolutionized image generation, achieving unprecedented levels of fidelity. However, consistent generation of high-quality images remains challenging partly due to the lack of conditioning mechanisms…

Text-to-image diffusion models have demonstrated remarkable capability in generating realistic images from arbitrary text prompts. However, they often produce inconsistent results for compositional prompts such as "two dogs" or "a penguin…

Current text-to-image (T2I) benchmarks evaluate models on rigid prompts, potentially underestimating true generative capabilities due to prompt sensitivity and creating biases that favor certain models while disadvantaging others. We…

Diffusion models have emerged as a dominant paradigm for generative modeling across a wide range of domains, including prompt-conditional generation. The vast majority of samplers, however, rely on forward discretization of the reverse…

Modern generative models exhibit unprecedented capabilities to generate extremely realistic data. However, given the inherent compositionality of the real world, reliable use of these models in practical applications requires that they…

Text-to-image diffusion models have advanced towards more controllable generation via supporting various additional conditions (e.g.,depth map, bounding box) beyond text. However, these models are learned based on the premise of perfect…

There is a rapidly growing interest in controlling consistency across multiple generated images using diffusion models. Among various methods, recent works have found that simply manipulating attention modules by concatenating features from…

Existing multi-modal image fusion methods fail to address the compound degradations presented in source images, resulting in fusion images plagued by noise, color bias, improper exposure, \textit{etc}. Additionally, these methods often…

Expressive music performance rendering involves interpreting symbolic scores with variations in timing, dynamics, articulation, and instrument-specific techniques, resulting in performances that capture musical can emotional intent. We…

Advances in generative models and sequence learning have greatly promoted research in dance motion generation, yet current methods still suffer from coarse semantic control and poor coherence in long sequences. In this work, we present…

Self-rewarding have emerged recently as a powerful tool in the field of Natural Language Processing (NLP), allowing language models to generate high-quality relevant responses by providing their own rewards during training. This innovative…

While score based generative models, or diffusion models, have found success in image synthesis, they are often coupled with text data or image label to be able to manipulate and conditionally generate images. Even though manipulation of…

Stable diffusion has demonstrated strong image synthesis ability to given text descriptions, suggesting it to contain strong semantic clue for grouping objects. The researchers have explored employing stable diffusion for training-free…

In text-to-image generation tasks, the advancements of diffusion models have facilitated the fidelity of generated results. However, these models encounter challenges when processing text prompts containing multiple entities and attributes.…

In this paper, we argue that iterative computation with diffusion models offers a powerful paradigm for not only generation but also visual perception tasks. We unify tasks such as depth estimation, optical flow, and amodal segmentation…

Recent advances in diffusion models have led to impressive image generation capabilities, but aligning these models with human preferences remains challenging. Reward-based fine-tuning using models trained on human feedback improves…

Unified multimodal understanding and generation models recently have achieve significant improvement in image generation capability, yet a large gap remains in instruction following and detail preservation compared to systems that tightly…

Recent Text-to-Image (T2I) generation models such as Stable Diffusion and Imagen have made significant progress in generating high-resolution images based on text descriptions. However, many generated images still suffer from issues such as…