Related papers: Training Free Stylized Abstraction
We propose Adaptive Multi-Style Fusion (AMSF), a reference-based training-free framework that enables controllable fusion of multiple reference styles in diffusion models. Most of the existing reference-based methods are limited by (a)…
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…
The study of causal abstractions bridges two integral components of human intelligence: the ability to determine cause and effect, and the ability to interpret complex patterns into abstract concepts. Formally, causal abstraction frameworks…
Humans naturally communicate through abstract concepts like "mood". However, current image editing benchmarks focus primarily on explicit, literal commands, leaving abstract instructions largely underexplored. In this work, we first…
Vision and Language (VL) models have demonstrated remarkable zero-shot performance in a variety of tasks. However, some aspects of complex language understanding still remain a challenge. We introduce the collective notion of Structured…
Recently, style transfer has received a lot of attention. While much of this research has aimed at speeding up processing, the approaches are still lacking from a principled, art historical standpoint: a style is more than just a single…
Diffusion-based image translation guided by semantic texts or a single target image has enabled flexible style transfer which is not limited to the specific domains. Unfortunately, due to the stochastic nature of diffusion models, it is…
We consider the problem of independently, in a disentangled fashion, controlling the outputs of text-to-image diffusion models with color and style attributes of a user-supplied reference image. We present the first training-free,…
Abstraction of a continuous-space model into a finite state and input dynamical model is a key step in formal controller synthesis tools. To date, these software tools have been limited to systems of modest size (typically $\leq$ 6…
Neural style transfer is a powerful computer vision technique that can incorporate the artistic "style" of one image to the "content" of another. The underlying theory behind the approach relies on the assumption that the style of an image…
Diffusion models achieve remarkable fidelity in image synthesis, yet precise control over their outputs for targeted editing remains challenging. A key step toward controllability is to identify interpretable directions in the model's…
Recent advances in image generation have made diffusion models powerful tools for creating high-quality images. However, their iterative denoising process makes understanding and interpreting their semantic latent spaces more challenging…
Large language models deliver strong generative performance but at the cost of massive parameter counts, memory use, and decoding latency. Prior work has shown that pruning and structured sparsity can preserve accuracy under substantial…
Tuning-free diffusion-based models have demonstrated significant potential in the realm of image personalization and customization. However, despite this notable progress, current models continue to grapple with several complex challenges…
Rectified flow models have become a de facto standard in image generation due to their stable sampling trajectories and high-fidelity outputs. Despite their strong generative capabilities, they face critical limitations in image editing…
In text-to-image models, consistent character generation is the task of achieving text alignment while maintaining the subject's appearance across different prompts. However, since style and appearance are often entangled, the existing…
Abstractive text summarization aims at compressing the information of a long source document into a rephrased, condensed summary. Despite advances in modeling techniques, abstractive summarization models still suffer from several key…
Driven by the remarkable progress in diffusion models, text-to-image generation has made significant strides, creating a pressing demand for automatic quality evaluation of generated images. Current state-of-the-art automatic evaluation…
This research introduces a transformative framework for integrating Vision-Enhanced Large Language Models (LLMs) with advanced transformer-based architectures to tackle challenges in high-resolution image synthesis and multimodal data…
Recent endeavors in Multimodal Large Language Models (MLLMs) aim to unify visual comprehension and generation by combining LLM and diffusion models, the state-of-the-art in each task, respectively. Existing approaches rely on spatial visual…