AI image generators are reshaping design and creative processes by leveraging advanced artificial intelligence methods. This article reviews notable tools and explains their impact on creative industries. Developments in text-to-image technology are contributing to new workflows and visual possibilities.
OpenAI has launched ChatGPT Images 2.0, a significant update to its AI-powered image generation model. The new version introduces improved reasoning capabilities, better handling of text and layouts, and enhanced multilingual support. OpenAI has also implemented advanced safety features and revised its pricing structure.
Google has announced the integration of Nano Banana 2 into its Gemini Personal Intelligence platform, enabling more intuitive text-to-image generation based on users’ Google account data. The feature allows subscribers to generate personalized images using natural language requests, with context drawn from sources like Gmail and Google Photos. The rollout begins in the U.S. and is expected to expand to more users and platforms.
Google’s Gemini AI now integrates with Google Photos, allowing users to generate personalized images using their own photo libraries. By opting in, subscribers enable the system to reference personal photos for more accurate and context-specific AI-generated content. The update streamlines previous workflows and raises questions about data privacy and user consent.
Google has introduced Nano Banana-powered image generation capabilities to its Gemini Personal Intelligence platform. The move is set to enhance Gemini’s abilities in creating images from text prompts, leveraging innovative AI-powered technology. The development places Gemini among the leading platforms in the competitive field of generative AI.
X has quietly released a new toggle in its iOS app allowing users to prevent Grok, its AI chatbot, from editing their uploaded photos. The move comes amid regulatory scrutiny and criticism of Grok’s image generation capabilities, particularly relating to nonconsensual and sexualized content. Neither X nor xAI has publicly commented on the limited feature.
Google has introduced Nano Banana 2, officially named Gemini 3.1 Flash Image, as its latest AI image generation model. The upgrade brings 4K resolution, faster image creation, and improved character consistency across multiple Google products and developer platforms. This release further standardizes AI-powered image generation in 141 countries.
Google has launched Nano Banana 2, a new AI model designed to accelerate image generation. The release underscores the company's ongoing investment in generative AI technology. The model aims to streamline the process for developers and businesses requiring faster visual content creation.
Adobe Firefly users can access unlimited AI-generated image creations at no cost until March 16. The offer, announced as part of Firefly's ongoing development, allows creators and professionals to test generative AI features without usage restrictions for a limited time.
KDnuggets' in-depth ComfyUI Crash Course demystifies AI-powered image generation, offering a hands-on guide to this popular open-source workflow tool. The course is aimed at making the advanced capabilities of tools like Stable Diffusion accessible to creators and developers across Europe and beyond.
Stay informed with curated insights delivered weekly to your inbox.