text to image News and Research

RSS

InstantDrag Accelerates Image Editing by Eliminating Masks and Text Prompts

Researchers developed InstantDrag, a new drag-based image editing tool that speeds up real-time photo edits without requiring masks or text prompts. The tool simplifies interactivity while maintaining high image quality.

19 Sep 2024

Advanced AI Model Boosts Image Personalization

Imagine Yourself, an advanced AI model, revolutionizes personalized image generation by eliminating the need for individual tuning. This model surpasses previous limitations with a novel approach, achieving superior identity preservation, text fidelity, and visual quality, as confirmed by human evaluations.

6 Aug 2024

Meta 3D AssetGen: Transforming 3D Modeling with AI

Meta 3D AssetGen significantly advances 3D mesh generation by utilizing a two-stage design for producing meshes with controllable, high-quality PBR materials. It outperforms existing methods in visual quality and alignment between the prompt and the generated meshes, making it ideal for applications in 3D graphics, animation, gaming, and AR/VR.

19 Jul 2024

Enhancing Geographic Diversity in Text-to-Image Models with c-VSG

Researchers introduced contextualized Vendi score guidance (c-VSG) to address geographic diversity limitations in text-to-image generative models. By integrating real-world exemplar images and leveraging the Vendi Score (VS), c-VSG significantly improved image diversity across geographically diverse datasets like GeoDE and DollarStreet.

1 Jul 2024

Flexible Image Editing with SceneDiffusion

Meta Research recently unveiled SceneDiffusion, an innovative method for flexible image layout rearrangement using diffusion models. This approach dynamically optimizes layered scene representations during sampling, enabling operations such as moving, resizing, cloning, and editing object appearances. SceneDiffusion requires no training and works swiftly with text-to-image diffusion models on diverse real-world images.

28 Jun 2024

Novel DIG Metrics for Fairer Image Generation

Researchers have introduced Decomposed-DIG, a set of metrics to evaluate geographic biases in text-to-image generative models by separately assessing objects and backgrounds in generated images. The study reveals significant regional disparities, particularly in Africa, and proposes a new prompting strategy to improve background diversity.

27 Jun 2024

Addressing Geographic Disparities in Text-to-Image Models

Researchers have investigated geographic biases in text-to-image generative models, revealing disparities in image outputs across different regions. They introduced three indicators to evaluate these biases, providing a comprehensive analysis to promote fairer AI-generated content.

27 Jun 2024

Robust Watermarking for Generative Images

Researchers introduced a method combining image watermarking with latent diffusion models (LDM) to embed invisible signatures in generated images, enabling future detection and identification while addressing ethical concerns in generative image modeling.

26 Jun 2024

Evaluating Text-to-Image Generative Models: A Global Perspective

Researchers found that current automated metrics inadequately capture the diverse human preferences necessary for evaluating text-to-image generative models across different regions like Africa, Europe, and Southeast Asia.

25 Jun 2024

IM-3D: Advancing Text-to-3D Modeling

Researchers introduce IM-3D, a pioneering approach utilizing video-based generators and Gaussian splatting reconstruction algorithms to directly produce high-quality 3D outputs from text prompts. IM-3D significantly improves efficiency, quality, and consistency in text-to-3D generation, showcasing superiority over existing methods through quantitative evaluations, human studies, and ablation analyses, thereby offering a promising solution for diverse applications requiring 3D asset generation from textual descriptions.

29 Feb 2024

Aesthetic Diffusion Model: Revolutionizing Interior Design with AI

Researchers introduced the Aesthetic Diffusion Model, utilizing AI to swiftly generate visually appealing interior designs based on text descriptions. By incorporating aesthetic scores, decoration styles, and spatial functionalities, the model streamlines the design process, enhancing efficiency and creativity while offering practical solutions for interior designers. Experimental results demonstrate the model's superiority, paving the way for future advancements in AI-driven interior design.

16 Feb 2024

Lumiere: A Breakthrough in Realistic Text-to-Video Generation

Researchers introduced Lumiere, a text-to-video diffusion model using space-time U-Net architecture, achieving state-of-the-art video generation with realistic motion and global temporal consistency.

1 Feb 2024

Enhancing Railroad Safety: RailFOD23 Dataset for Foreign Object Detection

Scientists present a pioneering approach to address the scarcity of datasets for foreign object detection on railroad power transmission lines. The article introduces the RailFOD23 dataset, comprising 14,615 images synthesized through a combination of manual and AI-based methods, providing a valuable resource for developing and benchmarking artificial intelligence models in the critical domain of railway safety.

23 Jan 2024

Instant3D: Accelerating Text-to-3D Generation with Efficient Neural Networks

This paper introduces Instant3D, a groundbreaking framework for rapid text-to-3D generation. Unlike existing methods that rely on time-consuming optimization, Instant3D achieves remarkable speed by utilizing a novel neural network that constructs a 3D triplane directly from a text prompt. With the capability to generate a 3D object in less than one second, the proposed approach demonstrates superior efficiency without compromising on qualitative and quantitative performance.

17 Nov 2023

Quality Diversity through Human Feedback (QDHF)

Researchers introduce a novel approach called Quality Diversity through Human Feedback (QDHF), which leverages human judgments to derive diversity metrics in Quality Diversity (QD) algorithms. This method, based on latent space projection and contrastive learning, offers a more adaptable and effective way to measure diversity, particularly in complex and abstract domains.

25 Oct 2023

CapGAN: A Breakthrough in Text-to-Image Synthesis

This article highlights the groundbreaking introduction of CapGAN, a novel model for generating images from textual descriptions. CapGAN leverages capsule networks within an adversarial framework to enhance the modeling of hierarchical relationships among object entities, resulting in the creation of diverse, meaningful, and realistic images.

11 Oct 2023

The Stable Signature: Rooting Watermarks in Latent Diffusion Models

Researchers have introduced a novel approach called "Stable Signature" that combines image watermarking and Latent Diffusion Models (LDMs) to address ethical concerns in generative image modeling. This method embeds invisible watermarks in generated images, allowing for future detection and identification, and demonstrates robustness even when images are modified.

6 Oct 2023

Creating Fair and Inclusive AI-Generated Images with ITI-GEN1

Researchers have introduced ITI-GEN1, an innovative approach that leverages reference images and inclusive tokens to generate inclusive images without extensive model retraining. This versatile and efficient method enhances inclusiveness and fine-grained attribute control in AI-generated images, offering a valuable tool for addressing challenges in image generation while ensuring fairness and representation.

14 Sep 2023

DiffusionEngine: Revolutionizing Data Scaling for Object Detection

Researchers have developed DiffusionEngine (DE), a novel data scaling engine that simplifies and improves the process of obtaining high-quality training data for object detection tasks. DE combines a pre-trained diffusion model with a Detection-Adapter (DA) to generate precise annotations efficiently, leading to significant performance gains in object detection algorithms.

13 Sep 2023

Efficient Text-to-Video Generation and Editing Using Simple Diffusion Adapter

Researchers have introduced an innovative approach to bridge the gap between Text-to-Image (T2I) AI technology and the lagging development of Text-to-Video (T2V) models. They propose a "Simple Diffusion Adapter" (SimDA) that efficiently adapts a strong T2I model for T2V tasks, incorporating lightweight spatial and temporal adapters.

23 Aug 2023