Related papers: Training-Free Object-Background Compositional T2I …
Diffusion models have enabled high-quality, conditional image editing capabilities. We propose to expand their arsenal, and demonstrate that off-the-shelf diffusion models can be used for a wide range of cross-domain compositing tasks.…
Image diffusion models, trained on massive image collections, have emerged as the most versatile image generator model in terms of quality and diversity. They support inverting real images and conditional (e.g., text) generation, making…
A significant research effort is focused on exploiting the amazing capacities of pretrained diffusion models for the editing of images.They either finetune the model, or invert the image in the latent space of the pretrained model. However,…
Style-conditioned text-to-image (T2I) generation with diffusion models requires both stable character structure and consistent, fine-grained style expression across diverse prompts. Existing approaches either rely on text-only prompting,…
Text-to-image (T2I) models excel on single-entity prompts but struggle with multi-entity scenes, often exhibiting attribute leakage, identity entanglement, and subject omissions. We present a principled theoretical framework that steers…
Achieving compositional alignment between textual descriptions and generated images - covering objects, attributes, and spatial relationships - remains a core challenge for modern text-to-image (T2I) models. Although diffusion-based…
Despite the recent success of multi-view diffusion models for text/image-based 3D asset generation, instruction-based editing of 3D assets lacks surprisingly far behind the quality of generation models. The main reason is that recent…
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…
Diffusion models excel at text-to-image generation, especially in subject-driven generation for personalized images. However, existing methods are inefficient due to the subject-specific fine-tuning, which is computationally intensive and…
Despite the impressive text-to-image (T2I) synthesis capabilities of diffusion models, they often struggle to understand compositional relationships between objects and attributes, especially in complex settings. Existing solutions have…
Modern deep models are trained on large real-world datasets, where data quality varies and redundancy is common. Data-centric approaches such as dataset pruning have shown promise in improving training efficiency and model performance.…
We introduce a novel, training-free approach for enhancing alignment in Transformer-based Text-Guided Diffusion Models (TGDMs). Existing TGDMs often struggle to generate semantically aligned images, particularly when dealing with complex…
Recently, integrating visual controls into text-to-image~(T2I) models, such as ControlNet method, has received significant attention for finer control capabilities. While various training-free methods make efforts to enhance prompt…
Recent text-to-image diffusion models have demonstrated an astonishing capacity to generate high-quality images. However, researchers mainly studied the way of synthesizing images with only text prompts. While some works have explored using…
Video-to-audio (V2A) generation aims to synthesize realistic and semantically aligned audio from silent videos, with potential applications in video editing, Foley sound design, and assistive multimedia. Although the excellent results,…
Diffusion model has demonstrated remarkable capability in video generation, which further sparks interest in introducing trajectory control into the generation process. While existing works mainly focus on training-based methods (e.g.,…
A plethora of text-guided image editing methods has recently been developed by leveraging the impressive capabilities of large-scale diffusion-based generative models especially Stable Diffusion. Despite the success of diffusion models in…
State-of-the-art T2I models are capable of generating high-resolution images given textual prompts. However, they still struggle with accurately depicting compositional scenes that specify multiple objects, attributes, and spatial…
Continual post-training adapts a single text-to-image diffusion model to learn new tasks without incurring the cost of separate models, but naive post-training causes forgetting of pretrained knowledge and undermines zero-shot…
Given an unconditional diffusion model and a predictor for a target property of interest (e.g., a classifier), the goal of training-free guidance is to generate samples with desirable target properties without additional training. Existing…