Generative AI for images, video, and creative media — Sora, DALL·E, Midjourney, Stable Diffusion, and more.
957 articles
Reference-based AI image editing lets creators keep composition intact while making targeted visual changes. It offers a practical way to maintain consistency across creative projects. Source: technology.org
Kuaishou's Kling AI 3.0 platform now generates cinematic 4K video at 60fps, featuring a Multi-Shot AI Director mode for storyboarding, motion control over camera paths and subject movement, plus lip sync in five languages. Source: barchart.com
OpenAI's latest image generation model claims improved detail and more accurate editing capabilities. A head-to-head comparison against Google's Nano Banana 2 tested both across six different categories to determine the stronger performer. Source: decrypt.co
Major content companies are pursuing legal action against AI developers using their material without permission, even as they simultaneously back other AI ventures. Many are repurposing their archives into structured data assets to feed AI systems. Source: chosun.com
ElevenLabs released version 2.5 of its Music generation tool, promising production-ready sound validated through blind listening tests. Lossless audio downloads are now included across all subscription tiers. Source: futurumgroup.com
A comprehensive survey in Multimedia Tools and Applications traces the evolution of deepfakes, from crude early face swaps to today's highly convincing fabrications. The paper also examines how detection methods are struggling to keep pace with rapidly improving generation techniques. Source: bioengineer.org
Text-to-image AI has come a long way from its early days of blurry, distorted outputs. Tools like ImagineArt now offer a reliable way to transform written prompts into finished, high-quality visuals. Source: ilounge.com
A look at how text-to-video AI has evolved by 2026, what separates production-ready tools from mere demos, and which platforms are actually worth using. The piece covers real-world use cases alongside the technology's current limitations. Source: tech-insider.org
A trend of generating retro 1980s-style portraits using ChatGPT has gone viral, but experts continue to flag privacy risks tied to uploading personal photos to AI chatbots. Concerns center on how facial data might be stored, used, or exposed. Source: hindustantimes.com
A new e-ink art frame lets owners simply describe what they want to see, like turning their dog into a Japanese woodblock print, and watch the artwork update on the wall. It combines conversational AI with color e-ink displays for a novel home-decor experience. Source: yankodesign.com
OpenAI has introduced GPT-6 Astra, described as its most capable model yet for business use. It brings improved reasoning, computer-use capabilities, and sharper writing and design judgment. Source: openai.com
More regulations now require labeling AI-generated content, but critics warn the practice may end up misleading rather than informing the public. Compliance can look thorough while doing little to actually clarify what's real. Source: cepa.org
ImgFree AI is presented as an unlimited AI image generator offering text-to-image and image-to-image editing along with various creative effects. The review covers its core features and practical everyday applications. Source: pctechmag.com
A new 2026 comparison from Newbury Park evaluates top AI tools for creating music videos. Freebeat took the top spot for its ability to automatically generate full-length videos synced to the beat. Source: streetinsider.com
APIXO's browser-based workspace now offers creators access to more than 30 video generation models, alongside image, audio, and API tools. The expansion aims to make the platform a broader hub for AI-driven content creation. Source: wboc.com
Amazon has made TwelveLabs' Marengo Embed 3.0 generally available as an embedding model within Amazon Bedrock Knowledge Bases. The update brings improved video and media search capabilities to the platform. Source: aws.amazon.com
OpenAI released ChatGPT Images 2.5 along with GPT-Image-2.5 Flare and Sunburst on September 8, 2026. The new version is 50% faster and priced between $0.006 and $0.211 per image. Source: tech-insider.org
A new workflow shows GPT-6 Astra analyzing a reference image, such as an excavator, to break it down into its component parts before guiding a 3D generation pipeline. The approach signals a shift toward large models acting as orchestrators of 3D modeling rather than just text or image generators. Source: eu.36kr.com
Following April's ChatGPT Images 2 update, OpenAI has now released ChatGPT Images 2.5, promising improved detail and more accurate editing capabilities. The new version arrives five months after its predecessor as OpenAI continues refining its image generation technology. Source: 9to5mac.com
Suno has launched a next-generation lineup of AI music-generation models developed in partnership with Warner Music Group, BMG, and Believe. The company will retire all of its previous models as it transitions fully to these newly licensed systems. Source: thenextweb.com