Related papers: Preserve Anything: Controllable Image Synthesis wi…
Generating images from text involving complex and novel object arrangements remains a significant challenge for current text-to-image (T2I) models. Although prior layout-based methods improve object arrangements using spatial constraints…
Although progress has been made for text-to-image synthesis, previous methods fall short of generalizing to unseen or underrepresented attribute compositions in the input text. Lacking compositionality could have severe implications for…
Recent advances in generative AI have dramatically improved photorealistic image synthesis, yet they fall short for studio-level multi-object compositing. This task demands simultaneous (i) near-perfect preservation of each item's identity,…
In the field of image processing, applying intricate semantic modifications within existing images remains an enduring challenge. This paper introduces a pioneering framework that integrates viewpoint information to enhance the control of…
We propose a new framework for conditional image synthesis from semantic layouts of any precision levels, ranging from pure text to a 2D semantic canvas with precise shapes. More specifically, the input layout consists of one or more…
Pretraining robust vision or multimodal foundation models (e.g., CLIP) relies on large-scale datasets that may be noisy, potentially misaligned, and have long-tail distributions. Previous works have shown promising results in augmenting…
Recent large-scale text-driven synthesis models have attracted much attention thanks to their remarkable capabilities of generating highly diverse images that follow given text prompts. Such text-based synthesis methods are particularly…
The field of text-to-image (T2I) generation has made significant progress in recent years, largely driven by advancements in diffusion models. Linguistic control enables effective content creation, but struggles with fine-grained control…
Controllable image synthesis with user scribbles has gained huge public interest with the recent advent of text-conditioned latent diffusion models. The user scribbles control the color composition while the text prompt provides control…
This study investigates identity-preserving image synthesis, an intriguing task in image generation that seeks to maintain a subject's identity while adding a personalized, stylistic touch. Traditional methods, such as Textual Inversion and…
Existing generative approaches for guided image synthesis of multi-object scenes typically rely on 2D controls in the image or text space. As a result, these methods struggle to maintain and respect consistent three-dimensional geometric…
Recent text-to-image (T2I) diffusion models show outstanding performance in generating high-quality images conditioned on textual prompts. However, they fail to semantically align the generated images with the prompts due to their limited…
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.…
Incorporating a customized object into image generation presents an attractive feature in text-to-image generation. However, existing optimization-based and encoder-based methods are hindered by drawbacks such as time-consuming…
Generating high-fidelity images of humans with fine-grained control over attributes such as hairstyle and clothing remains a core challenge in personalized text-to-image synthesis. While prior methods emphasize identity preservation from a…
Text-to-image synthesis models require the ability to generate diverse images while maintaining stability. To overcome this challenge, a number of methods have been proposed, including the collection of prompt-image datasets and the…
To enhance the controllability of text-to-image diffusion models, existing efforts like ControlNet incorporated image-based conditional controls. In this paper, we reveal that existing methods still face significant challenges in generating…
Controllable image synthesis with user scribbles is a topic of keen interest in the computer vision community. In this paper, for the first time we study the problem of photorealistic image synthesis from incomplete and primitive human…
Controllable 3D indoor scene synthesis stands at the forefront of technological progress, offering various applications like gaming, film, and augmented/virtual reality. The capability to stylize and de-couple objects within these scenarios…
Image composition has advanced significantly with large-scale pre-trained T2I diffusion models. Despite progress in same-domain composition, cross-domain composition remains under-explored. The main challenges are the stochastic nature of…