News/Image
Stability just launched Stable Diffusion 3.5 in big move for open-source AI art
A new era for text-to-image AI: Stability AI has launched Stable Diffusion 3.5, a significant update to its open-source text-to-image generative AI technology, aiming to reclaim leadership in the competitive field. The release introduces three new model variants: Stable Diffusion 3.5 Large (8 billion parameters), Large Turbo (a faster version), and Medium (2.6 billion parameters for edge computing). All models are available under the Stability AI Community License, allowing free non-commercial use and commercial use for entities with annual revenue under $1 million. Enterprise licenses are available for larger deployments, with models accessible via Stability AI's API and Hugging Face....
read Oct 18, 2024An alarming number of people are asking AI to create child pornography
AI-generated child exploitation material: A disturbing trend emerges; The recent hack of Muah.AI, a platform allowing users to create AI chatbots and request images, has exposed a concerning surge in attempts to produce child sexual abuse material (CSAM) using artificial intelligence. Muah.AI, with nearly 2 million registered users, has become a focal point for discussions about the ethical implications of AI-generated content. The hacked data, reviewed by security consultant Troy Hunt, revealed tens of thousands of prompts related to CSAM, including searches for "13-year-old" and "prepubescent" alongside sexual content. While Muah.AI confirmed the hack, they disputed the scale of CSAM-related...
read Oct 18, 2024Adobe unveils AI-powered 3D rotation tool for 2D drawings
Breakthrough in 3D visualization: Adobe unveiled an innovative tool called "Project Turntable" at its MAX conference, showcasing the ability to transform 2D vector images into rotatable 3D models instantly. The technology, still in the demo phase, can generate a 3D model from a 2D vector image in just four seconds. Users can rotate the resulting 3D model 360 degrees horizontally and partially vertically, providing a comprehensive view of the subject. The tool maintains the original artist's style and "essence" of the 2D artwork when creating the 3D model. Technical underpinnings: Project Turntable leverages advanced machine learning algorithms to extrapolate unseen...
read Oct 18, 20245 ways to get the best images out of your Midjourney prompts
AI-generated imagery evolves: Midjourney, a pioneering artificial image generation platform, continues to push the boundaries of digital creativity with its recent move to a web-based interface and enhanced features. Midjourney's transition from a Discord bot to a web platform has expanded its capabilities, including the addition of an editor for image resizing and AI-powered gap-filling. The platform maintains its position as one of the leading AI image generators, often outperforming competitors across various metrics. While Midjourney has become more user-friendly, mastering its nuances and hidden settings can significantly improve the quality and accuracy of generated images. Maximizing Midjourney's potential: Five...
read Oct 17, 2024Pollo AI joins the ranks of free AI video generators
AI-powered video creation made accessible: Pollo AI is a user-friendly option in the rapidly expanding field of AI video generators, offering both text-to-video and image-to-video capabilities for free. Developed by Hix.AI, Pollo AI joins the company's suite of generative AI tools, including the synthetic music platform Tad.ai. The platform allows users to create high-quality videos from text prompts or still images without requiring extensive technical knowledge or filmmaking experience. Pollo AI can generate fully realized productions, complete with animations and transitions, from simple text descriptions. Key features and functionality: Pollo AI's intuitive interface and diverse capabilities cater to a wide...
read Oct 17, 2024Google’s Gemini AI to receive major image generation upgrade
Google Gemini's image generation set for a major upgrade: Google is working on improving its Gemini AI's image generation capabilities, addressing a key limitation in the current system. Gemini's image generation, powered by Imagen 3, currently only produces square images with a 1:1 aspect ratio. Users have expressed frustration with the lack of flexibility in image dimensions, as cropping is the only available option to alter image sizes. Upcoming feature revealed in beta code: Android Authority has uncovered evidence of new image resizing options in a recent Google app beta. Code from the 15.41.34.29.arm64 beta version of the Google app...
read Oct 15, 2024Soon AI will turn static images into playable games
AI-generated playable worlds: A new frontier in gaming: Recent advancements in AI technology are enabling the creation of playable game environments from simple image prompts, potentially revolutionizing how games are designed and experienced. This breakthrough allows users to generate interactive game worlds based on real-world locations or imaginary scenes, opening up new possibilities for creative game design and player-generated content. Examples of this technology in action include creating platforming games from local play areas or sci-fi shooters based on everyday locations like gyms. Google has demonstrated the potential of this technology by recreating the classic game Doom using AI image...
read Oct 15, 2024New Photoshop plugin offers glimpse of where AI-powered interior design is heading
AI-powered design revolution: Adobe's new Photoshop plugin, "Project Hi-Fi," represents a significant leap forward in AI-assisted creative tools, transforming simple sketches into fully rendered digital images. The plugin utilizes Adobe's Firefly AI model to convert basic sketches or photographs into detailed, rendered images. Users can incorporate photographs, layers, and various elements beyond quick drawings to enhance their designs. In a demonstration, an Adobe designer showcased the plugin's capabilities by transforming a photo of an empty room into a rendered pink living room design using sketches and AI. Versatile functionality: Project Hi-Fi offers a range of features that streamline the design...
read Oct 15, 2024Missed the Northern Lights? Meta suggests fabricating images instead
AI-generated image controversy: Meta has sparked outrage on its Threads platform by suggesting users create fake Northern Lights photos using Meta AI, highlighting growing concerns about misinformation and the ethical use of AI image generators. Meta's Threads post, titled "POV: you missed the northern lights IRL, so you made your own with Meta AI," showcased AI-generated images of the Northern Lights over famous landmarks like the Golden Gate Bridge and Las Vegas. The post received significant backlash from users, with some criticizing Meta's apparent disregard for authentic photography and others expressing concern about the potential for spreading misinformation. Ethical implications...
read Oct 14, 2024PicsArt’s creative playbook: A vision AI in the creative industry
PicsArt's AI-driven evolution: PicsArt, a popular image and video editing platform with over 150 million monthly active users, is leveraging artificial intelligence to stay competitive and meet the evolving needs of its user base. Competitive landscape and challenges: PicsArt faces stiff competition in the mobile editing domain, with companies like Canva and Adobe offering similar products and features. Artavazd Mehrabyan, PicsArt's CTO, acknowledges the difficulty in maintaining a unique edge in the market, as competitors often copy successful features. The company was an early mover in smartphone-based editing, launching its all-in-one editing service for mobile in 2011. With the rise...
read Oct 14, 2024YouTube Music to let users create customized playlist thumbnails?
YouTube Music explores custom playlist thumbnails: YouTube Music is testing a feature that would allow users to upload their own custom images for playlist thumbnails, potentially enhancing personalization options for the music streaming platform. A user recently spotted a new pencil icon in the bottom-right corner of playlist artwork on the music.youtube.com website, indicating the possibility of custom image uploads. The feature appears to offer options to "Choose from library" and "Remove custom image," allowing users to select and crop images from their personal computers. Upon selection, the playlist page updates quickly, with the background also refreshing to reflect the...
read Oct 14, 2024The top 10 Leonardo AI alternatives to enhance your image creation
AI Image Generation Landscape: Alternatives to Leonardo AI: The field of AI image generation is rapidly evolving, with numerous platforms offering unique features and capabilities to cater to various creative needs and workflows. Leonardo AI, while popular, is just one of many options available for AI-powered image creation. The growing demand for AI-generated visuals has led to the development of diverse tools, each with its own strengths and specializations. Top Contenders in AI Image Generation: Midjourney stands out for its high-quality image output, utilizing Discord as its primary interface for generating images from text prompts. Simplified offers an intuitive platform...
read Oct 11, 2024What to do if Generative Fill is grayed out in Adobe Photoshop AI
Unlocking Adobe Photoshop's Generative Fill: Adobe's Generative Fill AI feature in Photoshop has generated excitement among users, but some have encountered issues accessing this innovative tool. Generative Fill is part of Adobe's Firefly and Sensei AI initiatives, available to Creative Cloud subscribers. Some users have found the feature disabled or grayed out, leading to frustration. A solution exists, but it's not immediately apparent to most users. Steps to enable Generative Fill: Verify software version: Check the Photoshop version by selecting "System Info" from the Help menu. Ensure you're running version 25.0.x or higher. Confirm you're logged into the Creative Cloud...
read Oct 10, 2024How to use Gemini AI to create better images
Google Gemini's Image Generation Upgrade: Google has enhanced its Gemini AI with Imagen 3, offering improved image generation capabilities for both free and paid users. Imagen 3 promises higher-quality images with crisper details, more vibrant colors, and fewer imperfections compared to its predecessor. The upgrade includes better text integration, more photorealistic renderings, and diverse artistic styles. Google DeepMind's evaluation found Imagen 3 outperforming competitors like DALL-E 3 and Midjourney v6 in user satisfaction tests. Accessing Gemini's New Image Generation Features: Users can utilize Gemini's enhanced image creation tools through multiple platforms. The Gemini website is accessible via web browsers on...
read Oct 10, 2024New AI image generator Flux runs fastest on RTX PCs
Groundbreaking image generation model introduced: Black Forest Labs has unveiled FLUX.1 AI, a new series of text-to-image generation models that excel in performance on NVIDIA RTX GPUs. FLUX.1 AI is built on the diffusion transformer (DiT) architecture, allowing for efficient handling of models with high parameter counts. The models are trained on 12 billion parameters, enabling high-quality image generation. NVIDIA RTX GPUs are crucial for running these computationally intensive models, with some variants unable to run on non-RTX GPUs without significant modifications. Model capabilities and features: FLUX.1 AI demonstrates exceptional prompt adherence and versatility in generating high-quality, diverse images. The...
read Oct 10, 2024Google Gemini AI image generator just rolled out to everyone for free
Google unveils Imagen 3: A new frontier in AI image generation: Google has launched Imagen 3, its most advanced AI image generator to date, making it freely available to all Gemini users on both mobile and desktop platforms. Key features and capabilities: Imagen 3 represents a significant leap forward in AI-generated imagery, offering improved instruction following and reduced visual artifacts compared to its predecessors. The model can generate a wide range of visual styles, from photorealistic landscapes to oil paintings and claymation scenes. Each prompt results in a single 2048x2048 JPEG image, which users can refine through iterative requests. Imagen...
read Oct 9, 2024Google brings AI image generation to Chromecast devices
AI-Powered Wallpapers Come to Google TV: Google has officially launched AI-generated wallpapers for Google TV devices, expanding the creative capabilities of smart home entertainment systems. The feature, announced last month, is now rolling out to Chromecast and other Google TV-enabled devices, as reported by 9to5Google. Users can access this new functionality through the device settings, specifically under Settings > System > Ambient Mode > Custom AI Art. How it works: The AI wallpaper generator offers users multiple ways to create unique, personalized backgrounds for their Google TV devices. Users can describe the image they want, utilizing the AI's text-to-image capabilities...
read Oct 9, 2024Google Photos may soon flag AI-generated images
AI-generated image detection coming to Google Photos: Google Photos is preparing to implement a feature that will help users identify AI-generated images by displaying IPTC metadata, potentially changing how users interact with and understand digital imagery. The upcoming feature, discovered through an APK teardown of Google Photos version 7.3, is not yet live but is expected to roll out in the near future. This development comes as a response to the rapid proliferation of AI-generated images and the growing need for transparency in digital media. Key metadata elements: The new feature will likely showcase specific IPTC (International Press Telecommunications Council)...
read Oct 9, 2024AI image showdown: Midjourney vs FLUX.1
AI image generation showdown: Midjourney 6.1 vs Flux 1.1 Pro: A comprehensive comparison of two leading AI image generators reveals Midjourney's continued dominance in creating realistic and visually compelling images across various scenarios. Test methodology and criteria: The comparison involved seven diverse prompts, each designed to challenge the AI models in different ways. The prompts covered landscapes, cityscapes, human portraits, futuristic scenes, fashion photography, alien environments, and motion photography. Each model received customized prompts to optimize its performance, recognizing the slightly different prompting techniques that work best for each. Images were evaluated based on detail and texture, lighting and shadows,...
read Oct 9, 2024Gemini will let users make precise edits to generated images
Google Gemini's AI Image Generator Upgrade: Google is enhancing Gemini's AI image generation capabilities in the latest Android beta, introducing new features that allow users to make precise edits to generated images. The upgrade was first reported by Android Authority in the Android beta version 15.40.31.29. The new feature enables users to make small tweaks to images generated by Gemini, such as changing specific elements of the image. In a demonstration, a user was able to generate an image of a dog wearing a hat and sunglasses, then successfully request to change the hat to a birthday hat. Competitive landscape:...
read Oct 8, 2024Authenticity and the evolving role of photographers in the AI era
AI's impact on photography: The rise of artificial intelligence in smartphone cameras is transforming the way we capture and perceive images, blurring the line between reality and digital enhancement. Apple, Google, and other tech giants are increasingly integrating AI-powered features into their smartphone cameras, automatically adjusting and enhancing photos. These AI enhancements have sparked debates about the nature of photography and the authenticity of images in the digital age. The Vergecast podcast recently explored this topic from multiple angles, featuring discussions with app developers and tech journalists. The evolution of smartphone photography: As smartphone cameras become more sophisticated, the process...
read Oct 8, 2024Google may release a feature to let you fine-tune AI-generated images
Gemini's image editing evolution: Google is enhancing its AI chatbot Gemini with a new feature that allows for more precise editing of generated images, marking a significant advancement in AI image manipulation capabilities. The new feature, discovered through an APK teardown of the Google beta app for Android (v15.40.31.29 beta), enables users to select specific areas of an AI-generated image for targeted editing. This functionality addresses a limitation in the current version of Gemini, where users can only refine images through text prompts without the ability to focus on particular sections. How the new feature works: The precise editing tool...
read Oct 7, 2024Artist challenges copyright ruling on AI-generated prize winner
AI-generated art sparks copyright controversy: The denial of copyright registration for Jason Allen's AI-assisted artwork "Théâtre D'opéra Spatial" has ignited a debate about the intersection of artificial intelligence and copyright law. Jason Allen, an artist who won a state fair art competition with his AI-generat-ed piece, is appealing the US Copyright Office's decision to refuse copyright registration for his work. The Copyright Office justified its denial by claiming the artwork was predominantly generated by AI and lacked sufficient human authorship to qualify for copyright protection. Allen's appeal challenges this decision, arguing that the Copyright Office misunderstood the creative process involved...
read Oct 7, 20245 AI image generators tested: the surprising winner revealed
The rise of AI image generation: AI-powered image creation has reached new heights, with some AI-generated images even winning photography awards and deceiving experts. AI image generators have become increasingly accessible, allowing anyone to create impressive images without artistic or technical skills. The quality of AI-generated images varies significantly between different platforms, with some excelling in realism while others struggle with common issues. Text generation within images remains a challenge for most AI image generators. Testing methodology: The author evaluated five popular AI image generators using progressively challenging prompts to identify their strengths and weaknesses. The test focused on realistic...
read