Generative AI for images, video, and creative media — Sora, DALL·E, Midjourney, Stable Diffusion, and more.
957 articles
MiniMax H3 has claimed first place in a video editing ranking that includes audio generation, with its weights made public. However, the released local version is limited to 768p, and parts of the full 2K pipeline remain undisclosed. Source: xenospectrum.com
A new image-to-video AI tool called Framia lets users create animated clips from still photos, skipping traditional video production entirely. Source: programminginsider.com
MiniMax H3 is an open-weight AI video generator built on multimodal reasoning, contextual regeneration, and an advanced architecture. Source: ca.news.yahoo.com
Buzzy.now has opened a dedicated page offering resources for creators and marketers using the Seedance 2.5 AI video generator. Source: usatoday.com
Making longer AI videos remains a challenge, but Dreamina's new Seedance 2.5 model now supports 30-second generations with up to 50 reference inputs, helping keep characters and scenes consistent. Source: manilatimes.net
ByteDance has globally launched Seedance 2.5, first available through Dreamina, aiming to reduce visual drift and rework needed when combining AI-generated clips. Source: prnewswire.com
On July 31, several major Chinese AI labs released new models within hours of each other, marking a notable milestone for the country's domestic large AI model ecosystem. The near-simultaneous launches underscore the intensifying pace of competition among Chinese developers. Source: eu.36kr.com
xAI's July 31 update to Grok Imagine Video 1.5 introduces text-to-video generation, native 1080p output priced at $0.25 per second, and voice cloning for consistent face-and-voice pairing. The release also adds support for combining up to seven reference elements within a single scene. Source: techtimes.com
Alphabet has disabled the AI image generation feature in Google Earth after it was used to produce misleading edits on real satellite imagery. The company says it needs to build stronger safeguards before reintroducing the tool. Source: reuters.com
Black Forest Labs' new FLUX 3 model aims to replace the traditional patchwork of separate tools for image generation, video synthesis and other tasks with a single multimodal system. According to early comparisons, it outperforms rivals like Seedance 2.0 and Grok in several benchmarks. Source: sitepoint.com
Google briefly offered AI-powered image editing within Google Earth's web version, but the feature was quickly misused to create misleading content. The company has pulled it while developing stronger safeguards against future abuse. Source: tech.yahoo.com
MiniMax's new H3 model produces 15-second clips in 2K resolution complete with native stereo audio. It works from a unified context that can combine text, images, video, and audio inputs. Source: marktechpost.com
Starting August 2, 2026, businesses that use AI to create images, audio, video, or in some cases text for professional purposes will be required to disclose that the content is AI-generated. The rule specifically targets so-called "deployers" within the advertising supply chain. Source: lewissilkin.com
MiniMax says it wants to support the open-source community and broad hardware compatibility with its new H3 model, which reportedly outperforms ByteDance's Seedance 2.0 in some tasks. Source: scmp.com
MiniMax has released H3, a multimodal video generation model that reportedly tops independent benchmarks for video editing among all tracked models. However, the launch comes as the company faces a copyright lawsuit tied to its video generation technology. Source: techtimes.com
The company's top video model now accepts text, image, and voice references and can generate footage up to 1080p resolution. Source: x.ai
This guide breaks down Google's Veo video-generation model, compares its different versions, and offers tips for using Veo 3 effectively, including prompting advice. Source: coursera.org
Under new EU rules, companies will have to clearly mark synthetic images, audio, and text that are designed to appear authentic, so users know when they're dealing with AI-made material. Source: theguardian.com
The final part of a series on AI transparency examines Article 50(4) of the EU AI Act, which sets out two separate labeling requirements for deepfakes and AI-generated text of public interest. Source: stibbe.com
The author describes creating an article's cover image not by manually clicking through tools, but by typing a shot description into a chat interface, where an AI agent handled the rest of the production process. Source: hackernoon.com