News/Image
xAI launches and then pulls its new AI image generator Aurora
The emergence and rapid disappearance of Aurora, an advanced AI image generation model, marks another development in X's growing artificial intelligence capabilities. Initial rollout and capabilities: Aurora appeared as a new image generation option within X's Grok AI assistant, demonstrating remarkable ability to create photorealistic images. The system excelled particularly at generating lifelike depictions of people and animals with near-photographic quality Aurora could accurately render well-known figures like Elon Musk, Sam Altman, and Donald Trump The model leveraged X's vast repository of user-generated content and web search data to inform its image creation Technical implementation and origins: Questions remain about...
read Dec 9, 2024Pixel Studio 1.4 adds AI sticker creator and Gboard integration
The latest update to Google's Pixel Studio app brings expanded creative capabilities with new AI-powered features and improved integration with other Google services. Key Features and Updates; Version 1.4 of Pixel Studio introduces significant enhancements to the app's sticker creation and sharing capabilities. Users can now generate stickers directly within the app using AI technology by either describing their desired sticker or creating one from an existing photo The update integrates Pixel Studio with Gboard, Google's keyboard app, allowing users to access and share stickers across any messaging application A new dedicated "Stickers" tab has been added to the "My...
read Dec 8, 2024Why Adobe Photoshop may just be the best AI photo editor anywhere
Key improvements: Adobe's latest release focuses on AI enhancements powered by Firefly Image Model 3, delivering more realistic and consistent results in generative features. The upgraded AI technology produces more believable imagery, with notably improved handling of textures, shadows, and overall detail New Generate Similar feature allows users to create variations based on preferred generated images Enhanced Detail option provides additional clarity to AI-generated content Interface and accessibility: Photoshop maintains its familiar layout while introducing subtle refinements to improve user workflow. The Contextual Task Bar now supports additional features for shapes, transformations, and gradients Interface remains consistent with previous versions,...
read Dec 8, 2024Grok’s new AI image generator Aurora will create photorealistic and copyrighted characters
The recent integration of "Aurora," a new AI image generation model, into X's Grok platform marks another significant development in the evolving landscape of AI-powered creative tools. Latest Development: X has expanded Grok's capabilities with Aurora, a new AI image generator that produces notably more photorealistic images than its predecessor. The new feature is accessible through the "Grok 2 + Aurora beta" option in the model selector Users can try the tool for a limited number of queries before encountering a paywall requiring an X Premium subscription Aurora represents a significant upgrade in image quality compared to Grok's previous image generation...
read Dec 6, 2024AI tool Ideogram now removes image backgrounds instantly
Key Innovation: Ideogram has introduced Advanced Background Removal, a feature that seamlessly integrates background removal capabilities into its AI image generation platform. The new tool eliminates the need for external photo editing software or manual background removal processes The feature is available to all paid subscribers without counting against image generation credits Users can further refine results using Canvas for detailed adjustments in complex areas Practical Applications: Ideogram's background removal tool enables streamlined creation of professional-grade design assets. Users can generate customized sticker sheets, logos, and product images with transparent backgrounds The platform maintains high accuracy in text generation and...
read Dec 4, 2024MIT researchers develop breakthrough method to turn 2D images to 3D shapes
Generative AI has expanded into the realm of 3D content creation, with MIT researchers making significant strides in transforming 2D image models into tools for generating three-dimensional shapes. Key breakthrough: MIT researchers have developed an enhanced technique for generating realistic 3D shapes using existing 2D image diffusion models, addressing previous limitations that produced blurry or cartoonish results. The team identified and corrected fundamental issues with Score Distillation Sampling (SDS), a technique that bridges 2D image generation models with 3D shape creation Their solution enables the creation of sharper, more realistic 3D shapes without requiring expensive model retraining or complex post-processing...
read Dec 3, 2024Google unveils AI video model ‘Veo’ in private preview
Google has expanded its creative AI offerings to include sophisticated video generation capabilities. Latest developments: Google has made its text-to-video generation model, Veo, available in private preview on the Vertex AI platform. Veo can create realistic videos at 24 or 30 frames per second based on text prompts The model can also generate videos from reference images while maintaining consistent style Initial demonstrations show promising results in addressing motion consistency, a common challenge in video generation Technical capabilities and features: Vertex AI users now have access to both Veo and the enhanced Imagen 3 text-to-image generator. Imagen 3 introduces new...
read Dec 2, 2024Ex Googler’s new site shows how much Google’s AI can glean from your photos
The growing concern over AI companies' access to and analysis of personal photos has led to the development of privacy-focused alternatives to mainstream cloud storage services. Privacy awakening: Former Google engineer Vishnu Mohandas left his position at the tech giant in 2020 after becoming increasingly concerned about how personal photos could be used to train AI systems. Mohandas developed Ente, an open-source photo storage service that features end-to-end encryption The platform aims to give users more control over their personal data while providing similar functionality to mainstream photo storage services Despite some limitations in features and ease of use compared...
read Nov 29, 2024Runway’s new ‘Frames’ image generator emphasizes stylistic consistency
The artificial intelligence company Runway AI has unveiled Frames, a new image generation model that emphasizes stylistic consistency and visual quality, marking a significant development in AI-generated imagery. Key innovation details: Runway's Frames model represents an advancement in maintaining consistent visual styles across multiple AI-generated images, particularly when creating cohesive "worlds" for video content. The model is being integrated into Runway's Gen-3 Alpha platform and API through a gradual rollout process Frames demonstrates enhanced capabilities in maintaining stylistic elements across multiple generations, addressing a common limitation in existing AI image models The technology shows particular strength in producing high-fidelity human...
read Nov 27, 2024Google’s ‘GenChess’ lets users design custom game pieces with AI
The intersection of artificial intelligence and classic board games continues to evolve with Google's latest experimental project, which brings a creative twist to the ancient game of chess. Project Overview: Google has launched GenChess, an AI experiment that allows users to create customized chess pieces using the sophisticated Imagen 3 model from Google DeepMind. The tool leverages the same AI technology that powers ImageFX and image creation in the Gemini chatbot Users can choose between classical chess pieces that maintain traditional forms or opt for more creative, experimental designs The system automatically generates a thematically complementary set for the opponent...
read Nov 26, 2024If you make 3D images, you need to try Nvidia’s Edify
Core technology overview: Nvidia Edify represents a significant advancement in 3D modeling technology, leveraging sophisticated algorithms to create detailed three-dimensional objects from simple inputs. The platform utilizes quad mesh models, which employ four-sided polygons to create natural edge flow and enable versatile subdivision modeling Physically based rendering materials simulate natural light interactions with 3D objects by considering attributes like base color and roughness The system synthesizes RGB values and surface contours through a diffusion model, creating realistic textures and surfaces [embed]https://www.youtube.com/watch?v=ROqB8xhKZ6U[/embed] Technical infrastructure: Edify operates within Nvidia's broader AI enterprise ecosystem, integrated with several key technological components. The platform is...
read Nov 26, 2024AI art shared by Elon Musk raises eyebrows in creative community
The key development: Elon Musk recently shared AI-animated versions of classical paintings on his social media platform X, generating discussion about AI's capabilities in art transformation. The AI-modified artworks include famous paintings by Gustave Courbet, Jacques-Louis David, Caspar David Friedrich, and Gustave Caillebotte The animations transform static scenes into dynamic panoramas with moving figures The original AI modifications were created by a social media user @dvorahfr Technical oversight reveals AI limitations: A notable error in the AI-generated content exposed current technological constraints in artificial intelligence art modification. An observer spotted a modern car appearing in the modified version of Caillebotte's...
read Nov 25, 2024Luma launches AI-powered creative platform and mobile app
Luma AI's Dream Machine, an AI video creation platform founded by former Google employees, is expanding its capabilities with a new interface, mobile app, and an advanced image generation model called Photon, marking a significant advancement in AI-powered creative tools. Core platform evolution: Dream Machine has transformed from a simple AI video model into a comprehensive creative platform serving both casual users and professionals. The platform has attracted over 25 million registered users since its June 2024 launch Dream Machine is now available on both web and iOS platforms The service operates on a subscription model with tiered pricing ranging...
read Nov 25, 2024Luma AI says its new Photon image generator is faster than any other AI model
The artificial intelligence image generation landscape continues to evolve with Luma AI's introduction of Photon, a new text-to-image model that emphasizes character creation and reusability. Key Features and Capabilities: Luma's Photon model builds upon their existing Dream Machine video generator, offering multi-image output and enhanced text rendering capabilities. The platform utilizes a proprietary Universal Transformer architecture that allegedly performs 800% faster and more cost-effectively than competing models Users can create reusable "characters" by uploading photos and using the "@character" command in prompts The system enables iterative prompt refinement and image customization for various creative applications Target Market and Applications: Photon...
read Nov 22, 2024Viral AI image generator FLUX.1 just got another big upgrade
Artificial intelligence image generation capabilities continue to advance with BlackForestLabs's latest update to its FLUX.1 platform, which has gained attention for producing highly realistic images without typical safety restrictions. Major platform upgrade: BlackForestLabs has launched FLUX.1 Tools, a comprehensive suite of image modification features that aims to enhance user control over AI-generated images. The new toolkit introduces four key features: Fill, Depth, Canny, and Redux, each designed to provide different image manipulation capabilities Fill enables both inpainting (modifying existing elements within an image) and outpainting (expanding images beyond their original boundaries) The Depth and Canny features utilize structural conditioning to...
read Nov 21, 2024A new AI’s controversial training method allows it to detect child abuse images
Online platform safety advances with groundbreaking AI technology aimed at identifying and preventing child exploitation content from being uploaded to the internet. Revolutionary development: Thorn and AI company Hive have created a first-of-its-kind artificial intelligence model designed to detect previously unknown child sexual abuse materials (CSAM) at the point of upload. The model expands Thorn's existing Safer detection tool by adding a new "Predict" feature that leverages machine learning technology Training data includes real CSAM content from the National Center for Missing and Exploited Children's CyberTipline The system generates risk scores to assist human content moderators in making faster decisions...
read Nov 18, 2024EditProAI is a new AI tool that’s going viral — Don’t fall for its scam
The rise of AI-generated content has created new opportunities for cybercriminals to distribute malware through fake AI tool websites. Latest cyber threat alert: A fraudulent AI image and video generator website called EditProAI is being used to distribute malware that targets both Windows and macOS systems. The malicious website appears legitimate with professional menus and privacy policies but delivers harmful malware when users click the "Get Now" button Windows users receive Lumma Stealer malware through a file named "Edit-ProAI-Setup-newest_release.exe" Mac users are targeted with AMOS malware via a file called "EditProAi_v.4.36.dmg" Distribution tactics: The cybercriminals behind EditProAI are leveraging both...
read Nov 17, 2024Barbers say more customers now request AI-suggested hairstyles
The rising popularity of AI-generated images is creating new challenges for hair stylists and barbers as customers increasingly bring machine-learning generated hairstyle references to their appointments. Current trend and immediate impact: Hair professionals are experiencing a surge in clients showing them AI-generated images for haircut inspiration, particularly notable in beauty salons across North America. Dean Allan, an Edmonton-based salon owner, reports seeing an increasing number of clients presenting AI-generated reference photos These AI images typically feature unrealistic characteristics, such as unusually thick hair and an artificial sheen The trend represents a shift from the traditional practice of bringing celebrity photos...
read Nov 16, 2024Struggling to find the right stock photo? Try Getty Images’ new AI tool
The rapidly evolving landscape of digital content creation is being transformed by new AI-powered tools that enable custom stock photo generation, with Getty Images being the latest major player to enter this space. Key Features and Functionality: Getty Images has introduced two new AI-powered features - Product Placement and Reference Image - within its Generative AI offerings for both Getty Images and iStock platforms. The Product Placement feature enables users to upload product images and generate custom backgrounds that seamlessly integrate with the product The Reference Image tool allows users to upload existing photos as templates, maintaining consistent color palettes...
read Nov 16, 2024Soon you’ll be able to make AI images directly within Google Docs
The integration of AI image generation capabilities directly into productivity software continues to expand as major tech companies compete to enhance their document creation tools. Latest development: Google is introducing a Gemini-powered AI image generator within Google Docs, enabling users to create custom visuals directly within their documents. The new feature will be accessible through the Insert > Image > Help me create an image menu option Users can generate images by providing text descriptions and selecting from various art styles including Photography and Sketch The tool offers multiple aspect ratio options including square, horizontal, and vertical formats to accommodate...
read Nov 14, 2024TikTok integrates Getty Images into AI-generated content
The integration of Getty Images into TikTok's AI advertising platform marks a significant expansion of creative tools available to digital marketers on the popular social media platform. The core development: TikTok has partnered with Getty Images to incorporate licensed visual content into Symphony Creative Studio, its AI-powered advertising generation tool. Advertisers can now access Getty's extensive library of licensed images and videos when creating AI-generated content The platform enables the creation of AI avatars that resemble real people for advertising purposes Symphony Creative Studio can generate video content from product descriptions and implement AI-powered language dubbing Technical capabilities: Symphony Creative...
read Nov 13, 2024How to protect your organization from cyber threats disguised as images
The rapid evolution of AI image recognition capabilities has revealed new security vulnerabilities through visual prompt injection attacks, where embedded text can manipulate AI models into ignoring their original instructions or performing undesired actions. Core concept explained: Visual prompt injection represents a novel security threat where malicious actors can embed text within images to override an AI system's intended behavior and force alternate responses. This technique exploits how multimodal AI models like GPT-4V process both images and text simultaneously By strategically placing text instructions within images, attackers can potentially manipulate the AI's interpretation and response The attack method works similarly...
read Nov 12, 2024Zerocam’s new mobile app completely rejects AI-tampered photos
Technology companies increasingly seek ways to counter AI's influence on digital photography, with the launch of Zerocam for Android representing a notable push toward photographic authenticity. App fundamentals: Zerocam has arrived on the Google Play Store as a minimalist camera application that eliminates post-processing effects and artificial enhancements. The app features only essential components: a viewfinder and shutter button Images are captured in RAW format with all HDR effects removed The interface intentionally excludes additional camera modes and features Key features and accessibility: The Android release follows a successful iOS launch that has already built a dedicated following. Users need...
read Nov 12, 2024Getty Images expands AI-powered custom content creation
Key platform updates: Getty Images has added new functionality to both its Generative AI by Getty Images and Generative AI by iStock platforms that enables users to upload custom reference and product images. Users can now incorporate their product images when generating AI artwork, particularly useful for creating custom backgrounds The platforms support reference image uploads to help maintain specific color palettes, patterns, and textures in the generated output These features are available across both Getty's main platform and its iStock subsidiary Technical foundation: The AI system is built on a carefully curated and ethically sourced dataset, utilizing Nvidia's Edify...
read