Tags: image editing

OpenAI’s ChatGPT Images 2.0 outperformed Google’s Gemini Nano Banana 2 in a series of practical image‑editing trials, delivering more realistic results across background swaps, cinematic tweaks, product mock‑ups and seasonal changes. While Nano Banana 2 proved faster, reviewers consistently favored ChatGPT Images for its attention to lighting, texture and facial fidelity, naming it the overall winner of the head‑to‑head comparison. Weiterlesen

Social media platform X announced worldwide rollout of automatic post translation and a new photo‑editing suite that responds to natural‑language prompts. Both features run on the company’s Grok models from xAI. Users can toggle translation on or off per post, and on iOS they can draw, add text, blur faces or sensitive data, or ask Grok to transform images with simple commands. Android support is slated for later this year. The updates follow earlier criticism of X’s image‑generation tools, which were previously limited to paying users. Weiterlesen

X and its sister company xAI have introduced a toggle in the iOS upload menu that lets users prevent the Grok chatbot from modifying uploaded photos. The change appears to respond to a recent scandal in which Grok generated millions of sexualized images, including thousands involving children, prompting two EU regulator investigations. While the feature is a visible step toward limiting misuse, it only blocks tagging Grok in a reply to edit an image, leaving other workarounds possible. Critics argue the measure is a token gesture that falls short of comprehensive protection. Weiterlesen

Google has introduced Nano Banana 2, an upgraded AI image generator that blends text rendering and web‑search capabilities with faster image creation. Integrated as the default model in the Gemini chatbot, Nano Banana 2 can pull real‑time information from the web to produce infographics and edit existing photos with photorealistic results. The tool is freely accessible through the Gemini app, Google Search, AI Studio, Cloud and other services, and includes watermarks to signal AI‑generated content. Weiterlesen

Elon Musk’s AI chatbot Grok continues to produce intimate deepfake images of men even after X introduced several safeguards, including a paywall and technological measures aimed at stopping the undressing of real people. Testing shows Grok readily removes clothing from fully clothed male photos, creates provocative outfits, and sometimes adds explicit details, while the restrictions appear to affect only certain public interfaces. The ongoing capability has drawn regulatory scrutiny worldwide, with investigations in multiple countries and concerns from lawmakers about the platform’s ability to comply with local laws. Weiterlesen

OpenAI has introduced GPT Image 1.5, an AI image‑synthesis model that runs within the same neural network that processes language prompts. The new model is reported to generate images up to four times faster and at roughly 20 percent lower cost than its predecessor. Integrated into ChatGPT, GPT Image 1.5 enables users to edit photos with simple text commands, from adding objects to changing clothing, while preserving facial likenesses. The rollout marks a shift toward more seamless, conversational image editing without needing specialized graphics skills. Weiterlesen

Google has rolled out Nano Banana Pro, a new AI‑powered image creation tool built on its Gemini model. Marketed toward professionals, the service promises studio‑quality designs, precise text rendering and the ability to blend or edit multiple images. Early testing shows the tool can adjust lighting, camera angles and generate infographics with readable text, but it sometimes misapplies edits—such as altering clothing or missing fine details. While the quality is impressive and the interface simple, users note occasional failures with complex tasks, especially around text fidelity and animal rendering. Weiterlesen

ChatGPT now lets users create and edit images directly within the chat interface. By selecting styles, using the built‑in editor, and accessing mobile‑specific tools, both free and Plus users can produce customized visuals for a variety of needs. The platform supports style changes, text integration, and uploading existing photos for transformation, making AI‑driven image creation more accessible than ever. Weiterlesen

OpenAI introduced GPT-5.1 as an incremental upgrade to its flagship model, GPT-5. The new version demonstrates tighter adherence to user instructions, a warmer conversational style, clearer logical explanations, and improved image‑editing consistency. Tests show GPT-5.1 following exact sentence limits, delivering concise yet friendly explanations, solving arithmetic problems with real‑world context, and preserving facial features when altering images. Visual classification also becomes more confident. While not a revolutionary leap, the refinements make GPT-5.1 a more reliable choice for everyday AI tasks. Weiterlesen

Google is finally rolling out its Nano Banana generative‑AI model in the Google Photos app for both Android and iOS. The new model replaces an older, less capable version and powers the Help Me Edit feature, allowing users to make precise edits by naming people in their photos and to apply creative style changes. The update follows a previous demo of Nano Banana and earlier promises to bring the technology to Photos. Weiterlesen

Google is rolling out its new AI model, Nano Banana, across several of its products. The model powers a major upgrade to image editing in Google Photos and adds a richer set of video‑generation styles to NotebookLM, including whiteboard, anime, retro print, and the original Classic mode. Users can now choose between Brief and Explainer video formats and steer the output with prompts. While a firm timeline isn’t set, Google says Nano Banana will appear in the Photos app within weeks, promising smoother conversational edits and a more consistent generative experience. Weiterlesen

Google has introduced Mixboard, an AI-driven mood board service that lets users generate and edit visual ideas from text prompts. The beta, available in the United States through Google Labs, leverages the company’s Nano Banana image‑editing model and Gemini AI. Mixboard aims to compete with Pinterest’s collage features and appeals to younger creators looking for quick, AI‑assisted design inspiration across home décor, events, fashion and more. Weiterlesen

Creating the right prompt is the single most important step for getting quality results from AI image generators such as Midjourney, DALL‑E, Leonardo and others. The article breaks down three essential prompt components—characters or elements, setting, and dimensions—before recommending style, color palette, and aesthetic descriptors to guide the model. It also warns against over‑using exclusionary language, suggests focusing on vibe and emotion, and offers practical troubleshooting tips like adjusting dimensions or using post‑generation editing tools. Following these guidelines can turn frustrating, distorted outputs into images that match the creator’s vision. Weiterlesen

Google's Gemini app has vaulted to the number‑one position on the U.S. App Store following the release of its Nano Banana image‑editing model. The new feature has driven a 45% month‑1‑over‑month increase in downloads, pushing September totals to 12.6 million, up from August's 8.7 million. Gemini also climbed the Google Play rankings, reaching No. 2 overall in the United States. The app has attracted 23 million first‑time users, generated $792,000 in September revenue, and now appears in the top five iPhone apps across 108 countries. Weiterlesen

Google's Gemini app has vaulted to the top of the U.S. App Store, displacing OpenAI's ChatGPT after the August launch of its Nano Banana image‑editing model. The new model drove a 45% month‑over‑month jump in downloads, pushing Gemini to #1 on September 12 after briefly holding the #2 spot. On Google Play the app rose to #2, while ChatGPT remains the platform leader. Gemini’s rapid growth has also boosted its revenue, with August earnings soaring to $1.6 million and September on track for a similar haul. The app now boasts tens of millions of new users and hundreds of millions of images shared. Weiterlesen

Creating effective prompts for AI image generators requires a clear description of subjects, setting, dimensions, style, and mood. Testing across platforms such as Google’s model, Midjourney, DALL‑E, Adobe Firefly, Leonardo, and Canva shows that a well‑structured prompt reduces unwanted artifacts and improves output quality. Prompt engineering involves specifying characters, location, aspect ratio, color palette, aesthetic, and emotional tone while avoiding exclusionary language that may be ignored. When results are unsatisfactory, tweaking the prompt or resetting settings can help, but the tools remain aids rather than replacements for human creativity. Weiterlesen