All articles tagged with #image generation
In a 30-factor, real-world test, OpenAI's ChatGPT Images 2.0 scored 97% (150 points) to Google's Gemini Nano Banana's 85% (131 points), with Images 2.0 delivering stronger context-aware image generation and better face fidelity, while Nano Banana struggled with text prompts, rendering details, and privacy-related concerns raised by unintended inclusion of prompt history in some results.
OpenAI’s Images 2.0, branded as the first image model with thinking capabilities, promises advanced text rendering and strategic design, but its demos—especially AI-generated football posters—have reignited social‑media chatter that graphic design is dead, with critics arguing outputs tend toward sameness and lack human soul, while proponents contend AI can augment designers rather than replace them.
Gary Marcus argues that ChatGPT’s new image engine is visually impressive but does not demonstrate true understanding. He points to labeling errors in bike diagrams and odd results from a custom tandem-bike prompt as evidence that the system can imitate understanding without grasping how parts function. The piece emphasizes that regurgitating images isn’t the same as real comprehension in AI.
Axios tests ChatGPT Images 2.0, which adds wider aspect ratios, a standard mode for all users and a paid 'thinking' mode with built-in reasoning. It produced a range of visuals—from personalized sympathy cards and old-style photo albums to trading cards and infographics—demonstrating strong capabilities but with occasional polish gaps and longer render times due to reasoning; a faux newspaper task briefly pulled older headlines before updating to current stories, signaling promising but imperfect results for business use.
OpenAI released ChatGPT Images 2.0, a more capable image-generation model that can output multiple images from a single prompt, render text more accurately, and handle non-English languages, using ChatGPT’s reasoning to fetch recent information and support customizable aspect ratios; English outputs are strongest, with improvements expected for other languages.
OpenAI is reportedly testing a new image-generation model (often nicknamed gpt-image-2) that produces highly realistic images and could help bolster ChatGPT toward 1 billion weekly active users, intensifying competition with Google in the AI imagery space.
Microsoft is using Copilot-generated images in Windows Learning Center posts to illustrate Windows 11 features, tagging them as 'AI Art Created by Copilot.' Critics say this AI-heavy marketing fuels backlash against Windows 11, as these generated visuals can misrepresent features and erode trust; the piece argues Microsoft should emphasize human creativity and tone down AI-promoted tools to win back user favor.
Google's Nano Banana 2 speeds up Gemini image generation, merging Nano Banana Pro features with faster rendering, real-time data support (like weather), better text accuracy, and a range of presets. It’s the default in many Gemini workflows, with usage limits that scale by plan (free users get fewer generations, Pro and Ultra use higher caps). Pro remains the benchmark for highest fidelity, but Nano Banana 2 delivers near-Pro quality more quickly; results can still include occasional spelling or realism glitches, and AI-generated images are watermarked with SynthID.
Google is expanding Nano Banana 2 (Gemini 3.1 Flash Image) to free users across Gemini, Google Search AI, and other platforms, making features once locked to Nano Banana Pro available to everyone. The model uses real-time data, web-sourced imagery, and Gemini’s knowledge base to render faster and more accurately, with legible text, localized translation, and greater creative control over lighting, textures, aspect ratios, and resolution from 512px to 4K. Nano Banana 2 replaces Nano Banana Pro as the default across the Gemini app and related tools, while Pro remains available for specialized tasks; the update also rolls out to AI Mode in Search, Lens, and Flow.
Google unveils Nano Banana 2, officially Gemini 3.1 Flash Image, a faster, Pro‑level image generator that replaces the previous Nano Banana models across the Gemini family. It leverages Gemini 3.1 knowledge for higher fidelity, can render up to five characters and 14 objects per workflow, offers richer textures and vibrant lighting, and supports more aspect ratios and up to 4K resolution. For now it’s the sole image generator in Gemini apps (Fast/Thinking/Pro); a Nano Banana 2 Pro variant may come later.
Bring A Trailer pulled a listing for a 1999 Cadillac DeVille after readers spotted AI-generated photos with inconsistent details, prompting apologies from BaT leadership and a discussion about tightening verification and inspection practices to prevent AI-driven misrepresentation in online car auctions.
Google Lens now supports Nano Banana, an image generation feature from the Gemini app, within Google Search, allowing users to create and transform images directly from their search interface, initially available in the US and India, with more regions coming soon.
Google has detailed the specific daily usage limits for Gemini, its AI platform, for both free and paid users, including prompt, image, and report quotas, with higher limits for premium subscribers like AI Pro and Ultra.
Researchers have developed an innovative AI image generator that uses light and minimal energy by leveraging optical components instead of traditional digital calculations, potentially revolutionizing energy-efficient AI applications.
OpenAI has updated ChatGPT's image model to include a built-in 'Style' feature, allowing users to easily generate images in various styles like anime or Ghibli without complex prompt engineering, and this feature is now available for free to all users.