September 12, 2026
Lightricks has released LTX-2.5, an open-weight video generation model capable of producing multi-shot scenes in a single pass. It also supports editing of real footage and exports in cinema-grade EXR format, making it a notable option for production-oriented workflows. The weights are available for fine-tuning and self-hosting.
ChatGPT's image generator has received an update aimed at producing results that more closely reflect the people and details present in source photos. PetaPixel put the model to the test by using it to transform a real person into a medieval knight. The results offer a practical look at how well the updated model handles likeness fidelity.
Shengshu has released Vidu Q3, the latest version of its AI video generation model, adding native audio generation alongside improvements to motion quality and prompt adherence. The update positions Vidu Q3 as a more complete tool for creators who need synchronized sound and visuals from a single model. It marks a notable step toward end-to-end video production within a unified AI system.
Runway has published a detailed look at how its product and engineering teams built Runway Agent, offering insight into the decisions and challenges that shaped the system. The post goes behind the scenes on the technical and design thinking involved in developing an AI agent within a creative video platform. It is a rare glimpse into the process behind one of the more ambitious features Runway has shipped.
Runway has published findings drawn from hundreds of enterprise clients using its tools for media production, outlining measurable gains in cost efficiency and turnaround speed. The report also looks ahead at how generative AI is beginning to reshape creative workflows in the media industry.
