Archive, page 8

Pinterest is testing a new feature called Restyle that uses generative AI to place furniture, decor, and lighting into photos of users' actual rooms. The tool is designed to bridge the gap between saved inspiration and real purchasing decisions. It represents Pinterest's clearest move yet toward making its visual catalog directly actionable.

Runway has launched Enhance Frame Rate, a model that upconverts video to broadcast-standard frame rates at any resolution. The company claims it processes footage up to seven times faster than competing interpolation tools. The feature is aimed at creators and professionals who need smooth, high-cadence output without lengthy render times.

Midjourney has pushed another round of updates to its alpha web platform, focusing on usability improvements and broader language support. The headline addition is Korean language support, joining the site's ongoing effort to make the interface more accessible globally. As with previous alpha updates, some features may still have rough edges while the team iterates quickly.

Adobe has announced Photoshop Elements 2027 and Premiere Elements 2027, bringing a range of AI-powered tools aimed at beginner and casual users. New features span generative image editing, video title creation, natural language search, and smarter asset organization. Both apps are available now.

An AI-generated retelling of The Odyssey from startup Fountain 0 has drawn sharp criticism for falling well short of basic cinematic standards. The film, called Odysseus: The Fall, was written, directed, and scored by company cofounder Ash Koosha, who also used his own likeness for the lead role. At two and a half hours, it is a steep ask for audiences already spoiled by Christopher Nolan's well-received adaptation of the same source material.

Runway has developed a synchronous moderation system designed to scan video frames for harmful content as they are generated, with a response time of under half a second. The system sits on top of Runway's existing safety infrastructure, adding a real-time layer of protection to its video generation pipeline. The move reflects the growing need to address safety challenges specific to streaming, frame-by-frame media output.

As generative AI tools become embedded in everyday production workflows, filmmakers who never touched them are discovering an uncomfortable reality: distributors, insurers, and legal teams now expect proof of human authorship, not just a claim of it. The documentation burden that has always shadowed indie film delivery is getting heavier. A producer and screenwriter breaks down what that means in practice.

A new film called "About a Hero" uses an AI trained on Werner Herzog's work - with his permission - to create a synthetic version of the legendary director as a narrative presence. Director Piotr Winiewicz is bringing the project to screenings alongside the AI itself, which will participate in Q&A sessions. A trailer for the docu-mystery has now debuted exclusively via IndieWire.

Superpose, a new camera app built by former TikTok executives, uses AI to analyze a user's photo and generate four suggested poses in response. The app aims to take the guesswork out of posing by giving people concrete, personalized visual guidance before they shoot. It sits at a practical intersection of generative AI and everyday photography.

ElevenLabs has expanded its Model Context Protocol server to include ElevenCreative, a suite of generation tools covering voice, music, images, and video. The update gives AI assistants like Claude, ChatGPT, and Cursor direct access to over 50 models through a single integration. This positions ElevenLabs as a broader creative platform rather than a specialist audio tool.

New York District Attorney Alvin Bragg announced the seizure of 12 websites that hosted non-consensual deepfake sexual imagery of celebrities. The sites collectively featured the likenesses of around 1,200 people rendered in what Bragg described as "hyper-realistic" sexual content. The action marks one of the more significant law enforcement moves against deepfake content platforms in the United States.

VOIDZ, a mixed-reality artist working anonymously since 2018, has released Ends Meat - a 95-second short film featuring 15 surreal visual interventions built using Runway. The project marks a significant expansion in scope from the artist's earlier work, which focused on short, discrete VFX shots. It offers a look at how generative video tools are enabling solo creators to sustain complex visual ideas across longer-form pieces.

Runway brought its Characters technology to SIGGRAPH's Real-Time Live! stage, demoing a generative character running in real time before an audience of researchers and practitioners. The team shares what the experience was like, what caught attendees off guard, and where the work is heading next.

Runway has introduced Media Router, a preference-optimized routing system built into its Runway Dev platform. Rather than relying on a single generative model, the system intelligently directs requests to the most suitable model based on the task at hand. It is the first tool of its kind purpose-built for generative media workflows.

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.

Netflix's Girish Balakrishnan and animation veteran Joel Kuwahara sat down to discuss how AI tools are entering creative production workflows and what that means for the craft. The conversation cuts through the noise to focus on what actually changes - and what doesn't - when AI becomes part of the process. It's a grounded look at AI's role in animation from two practitioners with real stakes in the outcome.

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.

Shengshu has released Vidu S1, the latest version of its generative video model. The update brings improvements to video quality, motion coherence, and overall generation capability. Vidu S1 continues the company's effort to compete in an increasingly crowded field of AI video tools.

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 outlined its research direction toward near-instant video generation, focusing on reducing the time between a prompt and the first rendered frame. The post explores how post-training base models to generate causally - frame by frame rather than all at once - makes real-time output increasingly feasible. The implications stretch across fields like education, gaming, robotics, and simulation.

Director Danny Boyle has openly acknowledged using generative AI to animate photographs in his latest film, Ink - a relatively rare instance of a major filmmaker publicly disclosing the technology's role in a finished theatrical release. The admission has drawn attention both for its transparency and for what it signals about AI's quiet integration into mainstream filmmaking. The technique involved bringing still images to life, a use case that has grown more capable and accessible as video gene

Hugging Face has published a detailed look at rebuilding AUTOMATIC1111, the widely used Stable Diffusion web UI, using Gradio Workflow. The post explores how the familiar interface and feature set can be reconstructed on a more modular, maintainable foundation. It offers a practical reference for developers looking to understand how classic image generation pipelines translate into the Gradio ecosystem.

Apple has updated its AI-powered Clean Up feature in iOS 27, building on the object-removal tool introduced in iOS 18. The upgrade promises more capable removal of unwanted elements from iPhone photos, with the tool handling more complex scenes than its predecessor.

A new short film called "Love, Rendered" uses generative AI tools developed with Google DeepMind to reconstruct moments from a real couple's life that were never captured on camera. The project explores how AI can fill in the visual gaps of a personal history spanning seven decades. It raises quiet but meaningful questions about memory, authenticity, and the role of AI in storytelling.