Tags: photorealism

Google’s new Nano Banana 2 AI image model promises speed without sacrificing the photorealistic quality that made its predecessor popular. While the tool excels at quick edits and style transformations, it still struggles with complex reflection removal, highlighting a trade‑off between speed and precision. Ler mais

Google has released Nano Banana 2, the latest version of its popular AI image editing tool built on the Gemini platform. The new model combines the speed of the original with the accuracy of the Pro tier, drawing on knowledge from Gemini 3 to reduce hallucinations and improve texture, lighting, and detail. Nano Banana 2 supports 4K resolution, varied aspect ratios, and clearer text generation. To help identify AI‑created images, Google now embeds invisible watermarks called content credentials. The upgrade arrives amid growing concerns about AI‑generated “slop” flooding social media, where many users struggle to spot synthetic content. Ler mais

Microsoft has introduced MAI‑Image‑1, its inaugural text‑to‑image generator built internally. Designed for speed, photorealism, and flexibility, the model aims to avoid the repetitive visual patterns common in other AI art tools. It has already entered the top ten on the LMArena leaderboard and will soon be integrated into Microsoft Copilot and Bing Image Creator. By curating training data and working with professional creatives, Microsoft hopes the model will deliver realistic images that fit directly into documents, ads, and presentations, strengthening its broader AI ecosystem. Ler mais