Zero-shot Text-guided Infinite Image Synthesis with LLM guidance
- URL: http://arxiv.org/abs/2407.12642v1
- Date: Wed, 17 Jul 2024 15:10:01 GMT
- Title: Zero-shot Text-guided Infinite Image Synthesis with LLM guidance
- Authors: Soyeong Kwon, Taegyeong Lee, Taehwan Kim,
- Abstract summary: There is a lack of text-image paired datasets with high-resolution and contextual diversity.
Expanding images based on text requires global coherence and rich local context understanding.
We propose a novel approach utilizing Large Language Models (LLMs) for both global coherence and local context understanding.
- Score: 2.531998650341267
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Text-guided image editing and generation methods have diverse real-world applications. However, text-guided infinite image synthesis faces several challenges. First, there is a lack of text-image paired datasets with high-resolution and contextual diversity. Second, expanding images based on text requires global coherence and rich local context understanding. Previous studies have mainly focused on limited categories, such as natural landscapes, and also required to train on high-resolution images with paired text. To address these challenges, we propose a novel approach utilizing Large Language Models (LLMs) for both global coherence and local context understanding, without any high-resolution text-image paired training dataset. We train the diffusion model to expand an image conditioned on global and local captions generated from the LLM and visual feature. At the inference stage, given an image and a global caption, we use the LLM to generate a next local caption to expand the input image. Then, we expand the image using the global caption, generated local caption and the visual feature to consider global consistency and spatial local context. In experiments, our model outperforms the baselines both quantitatively and qualitatively. Furthermore, our model demonstrates the capability of text-guided arbitrary-sized image generation in zero-shot manner with LLM guidance.
Related papers
- Visual Text Generation in the Wild [67.37458807253064]
We propose a visual text generator (termed SceneVTG) which can produce high-quality text images in the wild.
The proposed SceneVTG significantly outperforms traditional rendering-based methods and recent diffusion-based methods in terms of fidelity and reasonability.
The generated images provide superior utility for tasks involving text detection and text recognition.
arXiv Detail & Related papers (2024-07-19T09:08:20Z) - mTREE: Multi-Level Text-Guided Representation End-to-End Learning for Whole Slide Image Analysis [16.472295458683696]
Multi-modal learning adeptly integrates visual and textual data, but its application to histopathology image and text analysis remains challenging.
We introduce Multi-Level Text-Guided Representation End-to-End Learning (mTREE)
This novel text-guided approach effectively captures multi-scale Whole Slide Images (WSIs) by utilizing information from accompanying textual pathology information.
arXiv Detail & Related papers (2024-05-28T04:47:44Z) - GLoD: Composing Global Contexts and Local Details in Image Generation [0.0]
Global-Local Diffusion (textitGLoD) is a novel framework which allows simultaneous control over the global contexts and the local details.
It assigns multiple global and local prompts to corresponding layers and composes their noises to guide a denoising process.
Our framework enables complex global-local compositions, conditioning objects in the global prompt with the local prompts while preserving other unspecified identities.
arXiv Detail & Related papers (2024-04-23T18:39:57Z) - TextCoT: Zoom In for Enhanced Multimodal Text-Rich Image Understanding [91.30065932213758]
Large Multimodal Models (LMMs) have sparked a surge in research aimed at harnessing their remarkable reasoning abilities.
We propose TextCoT, a novel Chain-of-Thought framework for text-rich image understanding.
Our method is free of extra training, offering immediate plug-and-play functionality.
arXiv Detail & Related papers (2024-04-15T13:54:35Z) - SyCoCa: Symmetrizing Contrastive Captioners with Attentive Masking for
Multimodal Alignment [11.556516260190737]
Multimodal alignment between language and vision is the fundamental topic in current vision-language model research.
This paper proposes Contrastive Captioners (CoCa) to integrate Contrastive Language-Image Pretraining (CLIP) and Image Caption (IC) into a unified framework.
arXiv Detail & Related papers (2024-01-04T08:42:36Z) - SpaText: Spatio-Textual Representation for Controllable Image Generation [61.89548017729586]
SpaText is a new method for text-to-image generation using open-vocabulary scene control.
In addition to a global text prompt that describes the entire scene, the user provides a segmentation map.
We show its effectiveness on two state-of-the-art diffusion models: pixel-based and latent-conditional-based.
arXiv Detail & Related papers (2022-11-25T18:59:10Z) - Learning to Model Multimodal Semantic Alignment for Story Visualization [58.16484259508973]
Story visualization aims to generate a sequence of images to narrate each sentence in a multi-sentence story.
Current works face the problem of semantic misalignment because of their fixed architecture and diversity of input modalities.
We explore the semantic alignment between text and image representations by learning to match their semantic levels in the GAN-based generative model.
arXiv Detail & Related papers (2022-11-14T11:41:44Z) - Image-Specific Information Suppression and Implicit Local Alignment for
Text-based Person Search [61.24539128142504]
Text-based person search (TBPS) is a challenging task that aims to search pedestrian images with the same identity from an image gallery given a query text.
Most existing methods rely on explicitly generated local parts to model fine-grained correspondence between modalities.
We propose an efficient joint Multi-level Alignment Network (MANet) for TBPS, which can learn aligned image/text feature representations between modalities at multiple levels.
arXiv Detail & Related papers (2022-08-30T16:14:18Z) - Self-Supervised Image-to-Text and Text-to-Image Synthesis [23.587581181330123]
We propose a novel self-supervised deep learning based approach towards learning the cross-modal embedding spaces.
In our approach, we first obtain dense vector representations of images using StackGAN-based autoencoder model and also dense vector representations on sentence-level utilizing LSTM based text-autoencoder.
arXiv Detail & Related papers (2021-12-09T13:54:56Z) - Towards Open-World Text-Guided Face Image Generation and Manipulation [52.83401421019309]
We propose a unified framework for both face image generation and manipulation.
Our method supports open-world scenarios, including both image and text, without any re-training, fine-tuning, or post-processing.
arXiv Detail & Related papers (2021-04-18T16:56:07Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.