Related papers: ConceptPrism: Concept Disentanglement in Personali…
Recently, zero-shot image captioning has gained increasing attention, where only text data is available for training. The remarkable progress in text-to-image diffusion model presents the potential to resolve this task by employing…
The issue of generative pretraining for vision models has persisted as a long-standing conundrum. At present, the text-to-image (T2I) diffusion model demonstrates remarkable proficiency in generating high-definition images matching textual…
Concept Bottleneck Models (CBMs) enhance interpretability by predicting human-understandable concepts as intermediate representations. However, existing CBMs often suffer from input-to-concept mapping bias and limited controllability, which…
Diffusion-based models have achieved state-of-the-art performance on text-to-image synthesis tasks. However, one critical limitation of these models is the low fidelity of generated images with respect to the text description, such as…
Synthesizing visually impressive images that seamlessly align both text prompts and specific artistic styles remains a significant challenge in Text-to-Image (T2I) diffusion models. This paper introduces StyleBlend, a method designed to…
This study introduces Text-Guided Subject-Driven Image Inpainting, a novel task that combines text and exemplar images for image inpainting. While both text and exemplar images have been used independently in previous efforts, their…
Text-to-Image (T2I) generation has made significant advancements with the advent of diffusion models. These models exhibit remarkable abilities to produce images based on textual prompts. Current T2I models allow users to specify object…
Recent advances in Text-to-Image (T2I) diffusion models have transformed image generation, enabling significant progress in stylized generation using only a few style reference images. However, current diffusion-based methods struggle with…
While personalized text-to-image generation has enabled the learning of a single concept from multiple images, a more practical yet challenging scenario involves learning multiple concepts within a single image. However, existing works…
Image degradation synthesis is highly desirable in a wide variety of applications ranging from image restoration to simulating artistic effects. Existing models are designed to generate one specific or a narrow set of degradations, which…
Personalized text-to-image generation lets users fine-tune diffusion models into repositories of concept-specific checkpoints, but serving these repositories efficiently is difficult for two reasons: natural-language requests are often…
We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.). The proposed approach1 decouples training data generation…
Humans connect language and vision to perceive the world. How to build a similar connection for computers? One possible way is via visual concepts, which are text terms that relate to visually discriminative entities. We propose an…
Text-to-image (T2I) personalization allows users to guide the creative image generation process by combining their own visual concepts in natural language prompts. Recently, encoder-based techniques have emerged as a new effective approach…
Recent generative data augmentation methods conditioned on both image and text prompts struggle to balance between fidelity and diversity, as it is challenging to preserve essential image details while aligning with varied text prompts.…
Visual concept composition, which aims to integrate different elements from images and videos into a single, coherent visual output, still falls short in accurately extracting complex concepts from visual inputs and flexibly combining…
Given a small number of images of a subject, personalized image generation techniques can fine-tune large pre-trained text-to-image diffusion models to generate images of the subject in novel contexts, conditioned on text prompts. In doing…
The unlearning problem of deep learning models, once primarily an academic concern, has become a prevalent issue in the industry. The significant advances in text-to-image generation techniques have prompted global discussions on privacy,…
Recent advancements in text-to-image diffusion models have demonstrated their remarkable capability to generate high-quality images from textual prompts. However, increasing research indicates that these models memorize and replicate images…
Evaluating diffusion-based image-editing models is a crucial task in the field of Generative AI. Specifically, it is imperative to assess their capacity to execute diverse editing tasks while preserving the image content and realism. While…