Generative AI for images, video, and creative media — Sora, DALL·E, Midjourney, Stable Diffusion, and more.
952 articles
Alibaba's Qwen team has open-sourced Qwen-Image-2.1, a model that unifies text-to-image generation and image editing into one workflow. It aims to let users both create and refine images without switching tools. Source: technode.com
Gener8ion's music video "Storm" won early praise from fans including Charli XCX and Josh Kushner. Soon after, its distinctive look was widely imitated across AI-generated content. Source: insidehook.com
Building a marketing campaign often requires multiple connected assets — website imagery, social graphics, product shots, and a short video. A workflow pairing Kling 4.0 with GPT Image 2.5 shows how AI tools can generate all these pieces consistently. Source: appleworld.today
From local newsletters to climate campaigns, audiences increasingly expect video content rather than plain text. AI-powered video tools are now making it easier for independent creators and small outlets to meet that demand without big production budgets. Source: ipsnews.net
Qwen-Image-2.1 is a compact 7B-parameter visual generation model that combines three advanced image capabilities in one system. Its developers say it sets a new benchmark for open-source image generation. Source: eu.36kr.com
Mango Animate has launched a talking photo feature within its Mango AI video platform, letting users turn still portraits into speaking video clips. The tool aims to make animated faces sound and move naturally. Source: webwire.com
Google has launched Gemini 3.8 Live with an extended thinking mode, supporting 97 languages and allowing the AI to reason and respond simultaneously. The feature is rolling out across Gmail, Docs, and Search. Source: basic-tutorials.com
Tencent's new AI system Gander can process speech, images, and text while simultaneously running background tasks. A built-in 'cerebellum' module maintains the conversation flow, paired with a swappable component for handling other functions. Source: the-decoder.com
Video production is evolving faster than creators anticipated, with AI tools now replacing workflows that once demanded costly equipment and expertise. What used to require professional-grade gear is increasingly achievable with AI-driven software alone. Source: goodmenproject.com
The economics of video creation have quietly transformed — what once required a camera rig, editing software, a good microphone and a sizable budget can now be replicated with far less. The shift is opening new opportunities for solo creators and small shop owners alike. Source: ipsnews.net
A reviewer benchmarked Intel's Arc Pro B70 Creator, a GPU with 32GB of VRAM priced under 300,000 yen, by running the local LLM Qwen3.8 27B alongside the video generation model MiniMax H3. The test highlights that fitting an entire model into fast VRAM is key to achieving high-speed performance for both LLMs and generative video AI. Source: gigazine.net
Two experts from the University of Wollongong explain why detecting AI-generated content requires more than just examining an image itself. They use the viral rumor around Taylor Swift and Travis Kelce's wedding as a case study in how such misinformation spreads. Source: uow.edu.au
xAI has expanded Grok Imagine's video capabilities, moving beyond short clips toward full scene generation. The company teased the update via its official Grok account on September 18, inviting users to try the new feature. Source: basenor.com
HiDream's new model handles text, image, and video inputs to produce high-quality 1080p clips lasting 5 to 20 seconds. It's built natively to emphasize physical consistency across generated scenes. Source: wyomingnews.com
Alibaba's Qwen team unveiled Qwen3.8-Omni-Flash, described as its first omni-modal model designed for agentic tasks. It can process text, images, audio, and video while supporting tool use and a massive 1-million-token context window. Source: marktechpost.com
Short-form video has transformed how creators grow their audiences, with a single viral Reel sometimes outperforming months of polished YouTube content. This roundup highlights the leading AI tools tailored to that shift. Source: nerdbot.com
Happy Horse now combines text-to-video, image-to-video, reference-based generation, native audio, and multilingual lip sync into a single short-form video workflow. The update aims to streamline content creation for creators working across languages. Source: usatoday.com
AI-powered video generation has evolved well beyond simple text-to-clip novelty tools. The technology now supports more complex, production-ready workflows. Source: vocal.media
AI video renders aren't necessarily broken when they stall — they're usually just caught in one of several job states. The article explains how tools like Runway, Kling, and Higgsfield handle stuck or failed generations as of 2026. Source: hackernoon.com
HiDream.ai, a company focused on foundation models and generative AI, unveiled its new native omnimodal video model on September 17, 2026 in Beijing. The model is designed to maintain strong physical consistency across generated video content. Source: asianews.network