Alibaba’s Qwen team has released Qwen-Image-2512. This update improves their foundation model for generating images from text. The model is now available for public use and enterprise integration. According to the developers, this version focuses on three main areas: human realism, natural detail, and text rendering. The model aims to reduce the artificial appearance often …
AI image generators have become significantly more convincing by adopting an unexpected strategy: making their output look worse. Instead of creating glossy, overly perfect images, the latest models now replicate the imperfections typical of smartphone cameras. Allison Johnson writes for The Verge that early AI-generated images were easy to spot, featuring telltale signs like extra …
OpenAI has released an updated version of its image generation feature in ChatGPT. The new model creates images up to four times faster than the previous version and offers more precise editing capabilities. The company also introduced a dedicated section for image creation within ChatGPT’s interface. The updated model, available through ChatGPT for all users …
Adobe has launched integrations of Photoshop, Adobe Express and Adobe Acrobat directly within ChatGPT, making its creative and productivity tools available to the platform’s 800 million users. The company announced the launch on December 10, 2025, positioning it as a step toward making professional creative tools accessible through conversational interfaces. According to David Wadhwani, president …
The second season of the Amazon Prime series “House of David” used between 350 and 400 shots created with generative artificial intelligence. Kat Tenbarge reports for WIRED that this is more than four times the amount used in the show’s first season. Showrunner Jon Erwin said his production company, The Wonder Project, used AI to …
Researchers at New York University have created a new AI architecture that generates higher-quality images more efficiently. Ben Dickson reports for VentureBeat that the model, called Representation Autoencoders or RAE, improves an AI’s understanding of image content, which leads to better results. The new method challenges common practices in building diffusion models, the technology behind …
German AI startup Black Forest Labs, founded by the original creators of Stable Diffusion, has launched FLUX.2, a new family of AI models for generating and editing images. According to the company, the system is designed for professional creative workflows, aiming for reliability and control rather than one-off demonstrations. FLUX.2 introduces several key enhancements over …
A comprehensive comparison of major AI image generation models reveals that no single tool is best for all types of edits. The test, which included over 600 image generations, found that models from OpenAI, Google, and Seedream have distinct strengths and weaknesses depending on the user’s goal. The post in the LateNiteSoft blog explains that …
Google’s new image generator, officially named Gemini 3 Pro Image, fundamentally changes how AI creates visuals. Instead of immediately generating a result from a prompt, the model first enters a “Thinking Mode” to reason, critique, and correct its own plan. Stephen Smith writes in Intelligence by Intent that this new approach marks a significant shift. …
Google has launched a new image generation and editing model named Nano Banana Pro, officially called Gemini 3 Pro Image. The model is built on the company’s recently released Gemini 3 Pro large language model and introduces a range of new capabilities for creating and modifying images with a high degree of control and accuracy. …