News/Image
Getty Museum displays AI-generated photograph in groundbreaking addition to collection
The Getty Museum in Los Angeles has made history by acquiring its first AI-generated photograph, created by queer Costa Rican artist Matias Sauter Morera. The work, titled "Cristian en el Amor de Calle," explores the hidden cultural phenomenon of "pegamachos" - cowboys from Costa Rica's Guanacaste Coast who had secret encounters with young gay men in the 1970s. The groundbreaking acquisition: The Getty Museum's photography curator Paul Martineau selected this piece for inclusion in the upcoming exhibition "The Queer Lens: A History of Photography." The image depicts two young Latino men wearing blue leather jackets with gold embellishments in a...
read Feb 10, 2025AI image detection techniques every user should know
The rapid evolution of AI image generation tools has made it increasingly difficult to distinguish between real and artificial images. Tools like DALL-E 3, Midjourney, and Stable Diffusion can now create photorealistic images that challenge human perception. Key detection methods: Visual forensics and technological tools provide several ways to identify AI-generated images, though no single method is completely reliable. Reverse image searching helps verify the authenticity of newsworthy images by tracing them to their original sources Close examination of fine details often reveals telltale artifacts, inconsistencies, and unusual patterns that are typical of AI generation Anatomical irregularities, like extra fingers...
read Feb 8, 2025Mistral’s Le Chat offers text and image capabilities — and now it’s got a native mobile app
A French AI startup Mistral has launched Le Chat, a comprehensive AI chatbot platform that combines text interaction, document analysis, and image generation capabilities, now available on web and mobile platforms. Product Overview: Le Chat enters the AI assistant market with a robust set of features aimed at both individual users and teams. The platform offers text-based Q&A, PDF and image analysis, code interpretation, and web search functionality through a unified interface A new Canvas feature enables users to create and modify various types of content including documents, presentations, and code mockups The chatbot integrates with Mistral's Pixtral Large Language...
read Feb 5, 2025Galaxy S25 becomes first Android device to track photo edits made by AI
Samsung's Galaxy S25 series has become the first Android device to implement C2PA metadata standards for tracking AI-powered photo edits, marking a significant step toward digital media authenticity verification. Key implementation details: The Galaxy S25 lineup automatically adds specialized metadata and watermarks to images modified using Samsung's AI editing tools. When users edit photos with AI features, the system embeds C2PA metadata containing details about the device, AI tools used, and authentication credentials A visible watermark stating "AI-generated content" appears in the bottom left corner of edited images These content credentials can be viewed through Samsung's Gallery app or the...
read Feb 1, 2025How to train an AI image model on images of yourself
A new guide details how anyone can create personalized AI-generated images by training a model on their own photos, with the entire process taking under an hour and costing approximately $3. The fundamentals of AI image training; Low-Rank Adaptation (LoRA) technology allows for efficient customization of the Flux base model to recognize and generate images of specific individuals. The process requires associating a unique trigger word with 10-15 diverse personal photos Training costs average $2.50 per model, with subsequent image generations costing about $0.03 each The Replicate platform provides the necessary GPU computing power through a rental service model Technical...
read Jan 31, 2025How to create stunning AI images for free with Microsoft Image Creator
Microsoft's Image Creator has emerged as a powerful and accessible AI image generation tool, combining DALL-E 3's advanced technology with a user-friendly interface to transform text descriptions into custom visuals. This free service, available through bing.com/create or Microsoft Copilot, requires only a Microsoft account to access its comprehensive suite of features, including support for over 100 languages, built-in editing capabilities, and 15 daily "boosts" for expedited image generation. Key Features and Access: Microsoft Image Creator is freely available through bing.com/create or Microsoft Copilot, requiring only a Microsoft account to get started. Users receive 15 daily "boosts" for faster image generation...
read Jan 31, 2025iPhone Messages app now offers DALL-E AI image generation
Apple's latest iOS 18.2 update enables users to generate AI-created images directly within the Messages app using DALL·E through ChatGPT integration. New Feature Overview: The integration of ChatGPT with Apple Intelligence brings advanced AI image generation capabilities to supported iPhone models, specifically the iPhone 15 Pro and iPhone 16. The feature allows users to create custom images through voice commands in the Messages app DALL·E's image generation capabilities typically produce higher quality results compared to Apple's Image Playground Users can access this functionality without a ChatGPT account, though account holders can sign in for additional features Setup Process: The ChatGPT...
read Jan 29, 2025DeepSeek’s new image generator is another win for cost-effective AI
DeepSeek, a Chinese AI startup, has released Janus-Pro, a new open-source text-to-image AI model that claims to outperform established competitors like Stable Diffusion and DALL-E. Key Features and Capabilities: The Janus-Pro model family ranges from 1 billion to 7 billion parameters and operates using an autoregressive framework for image generation and analysis. The model is available under an MIT license, making it suitable for commercial use Users can download Janus-Pro through HuggingFace and GitHub platforms Smaller versions of the model are limited to analyzing images at 384 x 384 resolution Performance and Benchmarks: DeepSeek's internal testing shows promising results for...
read Jan 27, 2025DeepSeek claims its newest AI image model Janus-Pro surpasses Stable Diffusion, DALL-E 3
DeepSeek, a Chinese AI startup, has launched Janus-Pro, a new open-source AI image model that claims superior performance over established competitors like Stable Diffusion and DALL-E 3, despite resolution limitations. Key features and capabilities: Janus-Pro represents DeepSeek's latest entry into the competitive AI image generation market, with specific technical constraints and advantages. The model currently operates at a maximum resolution of 384x384 pixels, which is relatively small compared to other image generation tools The flagship version, Janus-Pro-7b, has demonstrated superior performance on two AI benchmark tests The model is being released as open-source, making it accessible to developers and researchers...
read Jan 18, 2025Runway’s new AI image generator Frames excels at the cinematic
Runway has launched Frames, a new AI image generation model that produces cinematic-quality visuals and integrates with the company's video generation tools. Key features and functionality: Frames provides advanced stylistic control and high visual fidelity, targeting professional creative industries including editorial, art direction, and production. The tool is available through Runway's Unlimited plan ($95/month or $912/year) and Enterprise plan ($1,500/year) Users can generate still images and seamlessly convert them to videos using Runway's Gen-3 Alpha Turbo model The system includes 19 preset visual styles, ranging from Vivid to Terracotta, that users can customize further Professional capabilities: Frames distinguishes itself through...
read Jan 17, 2025You can now fine-tune your own version of the FLUX AI image generator
Black Forest Labs has released FLUX Pro Finetuning API, enabling creators to customize AI image generation models with as few as five training images. Product Overview: The FLUX Pro Finetuning API allows customization of the company's FLUX Pro and FLUX Ultra image generation models, specifically targeting professionals in marketing, branding, and creative industries. The tool requires only 5-20 training images, with optional text descriptions, to create customized models Multiple modes are available including character, product, style, and general use cases The API integrates with FLUX.1 Fill, Depth, Canny, and Redux endpoints Image generation capabilities extend up to four megapixels in...
read Jan 14, 2025Samsung’s Sketch-to-Image feature will soon let you incorporate voice commands too
One of Samsung's next big reveals will reportedly include a new AI-powered Sketch to Image tool that allows users to combine voice and text inputs with drawings to generate images. Latest Features: Samsung is expanding the capabilities of its Galaxy AI-powered Sketch to Image tool within Drawing Assist, introducing multimodal input functionality that enhances creative possibilities. Users can now complement their sketches with typed text or voice commands to generate more detailed and specific images The upgraded tool allows for intuitive combinations, such as sketching a cat and adding "spacesuit" via text or voice to create a composite image Previously...
read Jan 9, 2025Microsoft rolls back Bing AI image tool amid quality concerns
Microsoft has rolled back its Bing AI image generator to a previous version following user complaints about deteriorating image quality after a December update. The situation: Microsoft's decision to revert its Bing Image Creator comes after implementing an upgraded version of the DALL-E 3 model that failed to meet user expectations. Users reported less detailed results and inaccurate interpretations of their prompts immediately following the December 18th upgrade Microsoft's head of search, Jordi Ribas, acknowledged the ability to reproduce reported issues The rollback process could take several weeks to complete User feedback and specific concerns: The deterioration in image quality...
read Jan 9, 2025How to use Meta AI to enhance your selfies
Meta's new AI photo editing tools allow users to creatively enhance and transform their selfies across Facebook, Instagram, Messenger, and WhatsApp platforms through simple chat-based interactions. Key Features and Functionality: Meta AI offers a range of photo manipulation capabilities that let users modify everything from basic appearance touchups to creating fantastical scenarios. Users can access the tools by logging into any Meta platform and navigating to the chat or story section The AI assistant can adjust cosmetic elements like glasses color and lipstick shade More advanced features include adding objects, changing backgrounds, and transforming the entire narrative of an image...
read Dec 22, 2024AI-generated street photography and what we lose by simulating our world with AI
The rising popularity of AI-generated imagery has sparked a critical debate about the fundamental nature of photography and authentic human experience in an increasingly digital world. Core argument: The distinction between traditional street photography and AI-generated images represents a crucial philosophical and practical divide in how we engage with reality. Traditional street photography requires physical presence, social interaction, and personal courage to capture genuine moments AI-generated imagery, while creative, bypasses these essential human experiences Some practitioners have begun referring to AI-generated street scenes as "photography," blurring important definitional lines Technical context: The term "photography" has specific meaning rooted in physics...
read Dec 21, 2024Renowned female artist brings AI-generated art to Times Square
Renowned artist Laurie Simmons is bringing AI-generated art to the iconic billboards of Times Square. Project overview; "Autofiction: Moving Pictures," a three-minute synchronized art display across 92 electronic billboards in Times Square, creates an unprecedented immersive experience at the crossroads of technology and traditional art. The installation debuts on December 20, 2024, at 11:57 PM, running nightly through December 30 The display features AI-generated images of contemplative women in color-coordinated rooms, creating a meta-commentary as hundreds of viewers look up at screens showing AI women looking down at their phones The project represents a significant scaling of digital art in...
read Dec 21, 2024TECNO’s new AI imaging tech will elevate smartphone photography
The latest advancements in smartphone photography technology are taking a significant leap forward with TECNO's introduction of new AI-powered image processing solutions, unveiled at their Future Lens 2024 event in Chongqing, China. Core innovation unveiled: TECNO has introduced a comprehensive suite of AI-powered photography features designed to transform how smartphone users capture and process images. The centerpiece of these innovations is the TECNO Image Matrix (TIM), which fundamentally restructures how imaging data is processed and optimized TIM employs a sophisticated layered structure that enhances four critical stages of image creation The system incorporates four specialized AI engines: AI RAW, AI...
read Dec 19, 2024Stable Diffusion 3.5 launches on Amazon Bedrock
The integration of Stable Diffusion 3.5 into Amazon Bedrock marks a significant development in enterprise AI image generation, offering businesses new capabilities for incorporating AI-generated images into their existing workflows. Key development: Stability AI and Amazon Web Services have partnered to make Stable Diffusion 3.5 Large available on the Amazon Bedrock service, making AWS the exclusive public cloud provider for Stability AI's flagship models. The integration enables enterprises to access multiple AI models through a single, unified API Research indicates most enterprises utilize multiple AI models simultaneously Organizations like the NFL and Stride Learning are already leveraging this integration Technical...
read Dec 18, 2024Google’s new AI image tool Whisk uses images instead of texts as prompts
AI image generation capabilities have taken another leap forward with Google's introduction of Whisk, a novel tool that creates AI-generated images from user-uploaded photos without requiring text input. Core functionality: Whisk allows users to combine multiple input images depicting subjects, settings, and styles into a single AI-generated creation. Users can upload photos representing different elements they want to incorporate without having to describe them in text The tool offers options to create variations like plushie toys, enamel pins, or stickers While text input is available for fine-tuning details, it's not required to generate images Technical architecture: Google's new image generation...
read Dec 17, 2024Amazon’s Nova AI models may be groundbreaking but details remain sparse
Amazon's recent release of its Nova AI models marked a significant move by the e-commerce and cloud computing giant to challenge existing leaders in generative AI. Key announcement details: Amazon unveiled its Nova series of frontier AI models at the AWS re:Invent conference, introducing specialized tools for video and image generation. The Nova series includes "Reel" for video generation and "Canvas" for image creation, positioning Amazon to compete directly with established offerings from OpenAI and Google These models leverage advanced techniques including retrieval-augmented-generation (RAG) and chain of thought approaches, which help AI systems access and utilize relevant information more effectively...
read Dec 16, 2024MidJourney unveils Pinterest-style moodboards and multi-model AI support
The AI image generation platform MidJourney has expanded its creative toolkit with new personalization features, including moodboards and multiple custom model profiles, enhancing the platform's utility for its 19 million users. Core feature updates: MidJourney's latest release introduces Pinterest-style moodboards and support for multiple AI model profiles, allowing users to maintain different versions of the platform's v6.1 image generator. Users can now upload collections of images to create inspiration boards that inform the AI's generation style The system adapts to the visual elements present in uploaded images to create unique style profiles Multiple personalization profiles can be created and managed...
read Dec 16, 2024Google’s new tool Whisk remixes your existing images with AI
Google's latest innovation that allows users to create new images by using existing images as prompts rather than relying solely on text descriptions. Core functionality: Google's new AI tool Whisk enables users to generate images by providing visual references for subject matter, scene composition, and artistic style. Users can upload multiple reference images for each category or use Google's auto-generated suggestions via a dice icon feature The system allows for optional text input to further refine the desired output Each generated image comes with an accompanying text prompt that can be modified for iterations Technical implementation: Whisk is powered by...
read Dec 15, 2024ByteDance ex-intern accused of sabotage wins prestigious AI award
ByteDance's ongoing legal dispute with a former intern has intersected with one of artificial intelligence's most prestigious research awards, highlighting tensions between academic achievement and professional conduct in the AI industry. The breakthrough research: A paper introducing a novel method for AI image generation, authored primarily by former ByteDance intern Keyu Tian, received the coveted Best Paper Award at the Neural Information Processing Systems (NeurIPS) conference. The research presents an innovative approach called "Visual Autoregressive Modeling" that could make AI image and video generation more computationally efficient This methodology could significantly reduce the computing resources needed for complex AI visual...
read Dec 14, 2024Lawsuit claims Photobucket sold user biometric data illegally
Photobucket faces a class action lawsuit over allegations of selling users' biometric data to AI companies without proper consent, potentially affecting up to 100 million users and billions of photos stored on the platform since 2003. Key allegations and scope: The lawsuit targets Photobucket's recent privacy policy update that revealed plans to sell users' photos, including biometric data like face and iris scans, to AI training companies. Two distinct classes are represented: users who uploaded photos between 2003 and May 2024, and non-users whose images appear in uploaded photos The company claimed access to approximately 6.5 billion public images eligible...
read