#image-generation

#image-generation

Google aims to enhance the image generation capabilities of Nano Banana 2 by utilizing personalized data from users' Google accounts, including their YouTube history and Google Photos. This integration allows for more relevant and tailored image outputs without requiring users to provide extensive context.

On Friday morning, the Grok account on X started responding to some users' requests with a message saying that image generation and editing are "currently limited to paying subscribers." The message also includes a link pushing people towards the social media platform's $395 annual subscription tier. In one test of the system requesting Grok create an image of a tree, the system returned the same message.

Following the release of GPT-5.2 last week, OpenAI has begun rolling out a new image generation model. The company says the updated ChatGPT Images is four times faster than its predecessor. If you're a frequent ChatGPT user, you'll know it can sometimes take a while for OpenAI's servers to create images, particularly during peak times and if you're not paying for ChatGPT Plus. In that respect, any improvement in speed is welcome.

Search continues to ship 🚀 Built on Gemini 3 Pro, Nano Banana Pro is available in Search, starting with AI Mode, on day 1 for Google AI Pro or Ultra subscribers in the U.S. https://t.co/OrkyHrNMzS- Robby Stein (@rmstein) November 20, 2025 AI Mode query ⬆️ Create a detailed infographic for college students on trophic levels and energy transfer in ecosystems. The infographic should feature an ecological pyramid (energy or biomass), with definitions of producers, primary, secondary, and tertiary consumers, and...- Nick Fox (@thefox) November 20, 2025

Nano Banana Pro can help you visualize any idea and design anything - from prototypes, to representing data as infographics, to turning handwritten notes into diagrams.

The AI-powered image editor makes it easy to change images with natural language user prompts. Also: You can test Microsoft's new in-house AI image generator model now - here's how The model became generally available earlier this month, but was only accessible in the Gemini API or for enterprise use via Vertex AI. Here's how to get started in these recently added applications.

In addition to being generally available, Gemini 2.5 Flash Image now comes with 10 aspect ratios across four styles (landscape, square, portrait, and "flexible"), enabling "effortless content creation across various formats, from cinematic landscapes to vertical social media posts," Google wrote in its announcement. The company also published developer docs and a " cookbook" to help users get started with Gemini 2.5 Flash Image, which costs $0.039 per image.

AI is not a replacement for human creativity, but rather a powerful tool for ideation and concept generation. When used correctly, AI can amplify your creativity by sparking fresh ideas and streamlining tedious tasks. In this blog, we explore how creators can leverage AI to supercharge their portfolio-building process - from breaking through creative blocks to visualizing concepts instantly and crafting compelling case studies.

Google is launching a new AI concepting tool that lets you create moodboards to explore design ideas. The Mixboard Google Labs experiment gives users an open canvas to create projects from pre-populated board templates or text prompts using Google's Gemini 2.5 Flash model. The experimental tool is available through public beta in the US. The format is visually similar to platforms like FigJam or Adobe's Firefly Boards, so this isn't a unique concept, but it's interesting to see Google developing more design-based apps.

For example, when someone asks 'why is there low water pressure after installing a new sink' when they encounter a problem during a home renovation, AI Overviews may provide some helpful tips on how to fix it, as well as a useful ad for a plumber, who can come to the rescue to fix that bathroom.", a new feature to help you create even more brand-safe creative, steering Google AI to create high-performing text assets that meet your brand and business requirements.

In 2023, a group of researchers from the University of California, Berkeley, started Chatbot Arena, now called LMArena. It allows people to compare different AI models with prompts and determine which is better. Users can vote for how well models perform and compare them on a leaderboard. LMArena saw a tenfold traffic spike in August when a mysterious new AI text-to-image and image editing model, Nano Banana, went viral for churning out impressive images and photo edits.

In testing the predictive power of pretraining concept frequencies, the results show a clear scaling trend where increased frequency directly correlates with improved zero-shot performance across different prompting strategies and evaluation metrics.