Generative AI for images, video, and creative media — Sora, DALL·E, Midjourney, Stable Diffusion, and more.
952 articles
Google's updated Gemini Omni 1.1 Flash can now generate AI videos lasting up to 40 seconds, a notable jump from previous limits. However, the touted 4K resolution is achieved through upscaling rather than native rendering. Source: xenospectrum.com
Multimodal AI refers to systems that combine text, image, and audio understanding within a single model instead of relying on separate tools. This approach enables more natural interactions and broader use cases, from analyzing photos to processing spoken language. Source: sqmagazine.co.uk
OpenAI highlights how ChatGPT's image generation feature can create visuals in various formats and dimensions to match users' needs. The tool aims to make bringing creative concepts to life faster and more flexible. Source: startuphub.ai
This installment continues a series exploring the evolution of AI technology, tracing its progression from conversational chatbots toward AI embedded in physical systems and robotics. It frames this shift as one of several major waves shaping the industry's future. Source: patmcguinness.substack.com
A comprehensive roundup ranks the top AI image generators for 2026, comparing their capabilities, pricing plans, and output quality. The guide aims to help users pick the right tool for their creative or business needs. Source: nerdbot.com
Platforms that combine several AI video models in one workspace are becoming increasingly popular this year. They let creators mix outputs from different engines to get better results than relying on a single model. Source: findarticles.com
The team behind ByteDance's popular imaging apps FaceU and CapCut is now launching a new AI video venture called Flova. The move signals continued momentum from ByteDance-linked talent moving into generative video. Source: tradingview.com
Many AI video generators struggle to maintain consistent camera direction and spatial continuity between shots. A new workflow approach is proposed to keep screen direction coherent across generated clips. Source: hackernoon.com
Companies are increasingly using AI-generated video content to attract job candidates and promote their employer brand. The technology allows recruiters to produce polished, personalized video campaigns faster and at lower cost. Source: onrec.com
Reve has released an API enabling developers to generate high-resolution 4K images through its platform. The offering targets businesses and developers looking to integrate advanced image generation directly into their own applications. Source: dynamicbusiness.com
ByteDance has reached a worldwide agreement with Hollywood studios covering copyright protections related to AI-generated content. The deal aims to set ground rules for how AI tools can use and reproduce copyrighted film material. Source: campaignme.com
Stability AI, the company behind the popular image generator Stable Diffusion, has closed a new funding round worth $76 million. The fresh capital is expected to support further development of its AI image generation technology. Source: techcrunch.com
Researchers have introduced STARFlow2, a new approach that merges large language models with normalizing flow techniques to enable unified generation across different data types. The method targets more consistent and flexible multimodal content creation. Source: machinelearning.apple.com
A short film created with AI has gone viral in China by reimagining classic monster imagery as a story centered on human emotion and experience. The film's unusual blend of horror aesthetics and heartfelt narrative has drawn widespread attention online. Source: globaltimes.cn
A new guide rounds up the ten best free AI image generation tools available in 2026, focusing on what users can actually achieve without paying. It highlights the real capabilities and limitations of each free option. Source: wptavern.com
A new piece explores how AI tools are enabling ecommerce businesses to handle more of their advertising video production internally rather than outsourcing it. The shift is expected to cut costs and speed up content creation for online sellers. Source: financialcontent.com
A new academic overview brings together the theoretical foundations, architectural designs, and practical applications of diffusion models in deep generative learning. The work aims to provide a unified framework for understanding this widely used generative AI approach. Source: bioengineer.org
A new roundup highlights ten AI image generation tools best suited for producing consistent visual series across multiple images. The list targets creators working on projects that need coherent characters, styles, or scenes. Source: newwavemagazine.com
Alibaba's new video generation model Wan3.0 can produce clips up to 30 seconds long from text prompts, PDFs, and PowerPoint files. A 30-second 1080p video costs $6 to generate. Source: the-decoder.com
Alibaba officially released Wan3.0, the latest version of its AI video generation model, on Monday. The launch came just one day after the Chinese tech giant completed a major share sale. Source: technology.org