Twice a week, the most important stories in image and video generation - new models, notable research, and meaningful product releases - distilled into a 2-minute read. No hype, no filler.
Free. Unsubscribe any time. No spam, ever.
Runway has introduced a unified pricing structure, consolidating its plans to simplify how users access its suite of generative video and image tools. The change appears aimed at reducing friction for both individual creators and teams evaluating the platform. Here is what the new pricing model means in practice.
A heavily AI-edited photograph has taken first place at a state fair photography competition, sparking anger among photographers who feel the win undermines the integrity of the medium. The controversy was significant enough that organizers have already announced rule changes for next year's contest.
OpenAI has reportedly acquired Glass Imaging, a computational photography and image processing startup, for around $300 million. The deal signals a continued push by OpenAI into the visual media space, beyond its existing generative image tools. Glass Imaging was known for its AI-driven photo enhancement technology, particularly for improving image quality on mobile devices.
Meta's Oversight Board has directed the company to take down two AI-generated deepfake videos from Facebook, marking a notable exercise of the board's authority over synthetic media content. The ruling also calls on Meta to strengthen its broader policies around deepfake detection and removal. It signals growing pressure on major platforms to develop more consistent and enforceable standards for AI-generated misinformation.
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.
Amazon Prime Video has introduced an AI-assisted lip sync feature that adjusts an actor's mouth movements to match dubbed audio. The tool is currently limited to the English dub of the German series Maxton Hall, with plans to roll it out to more titles over time.
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.
OpenAI is updating its image generation offering with ChatGPT Images 2.5, introducing two distinct models - Flare for faster outputs and Sunburst for more precise editing. The rollout appears uneven, with different users receiving different model access at different times. Early testing suggests the improvements are real but not universally available yet.
OpenAI has released ChatGPT Images 2.5, an updated image generation system that promises faster output and more accurate multi-turn editing. The update also introduces a Sketch feature, template support, and two new API models for developers. The changes build on the image capabilities OpenAI has been expanding within ChatGPT over the past year.
Lightricks has released LTXV, a video generation model designed for controllable, high-quality output. The model supports long-form clips, keyframe-based control, and advanced conditioning options. It positions itself as a tool for creators who need precise influence over the generation process.
Lightricks has released LTX-2, an AI video generation model aimed at professional and production workflows. It supports native 4K output, high frame rates, and extended long-form content generation. The model is designed with precise creative control in mind, targeting studios and creators who need reliable, consistent results.
Lightricks has quietly shifted LTX-2.3 into legacy status as LTX-2.5 takes over as the current recommended model. LTX-2.3 remains fully supported and still offers open weights, synchronized audio, and native portrait video generation. For teams already building on it, nothing breaks - but new projects are now steered toward the newer release.
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.
Apple's Clean Up tool, introduced in iOS 18, gets a notable upgrade in iOS 27, making it easier to remove unwanted objects from photos directly on iPhone. The feature uses on-device AI to identify and erase distracting elements while filling in the background naturally. Engadget walks through exactly how to use the updated tool in the iPhone Photos app.
Runway has launched native plugins for Adobe Premiere Pro and After Effects, bringing its generative image and video tools directly into two of the most widely used editing applications. Users can generate media, restyle timeline footage, and place results into their compositions or sequences without leaving the Adobe environment.
OpenAI has introduced a drawing-based input tool called Sketch alongside the release of ChatGPT Images 2.5. Users can now draw a rough doodle directly inside the ChatGPT interface and use it as a visual reference for image generation. The feature is activated by typing @Sketch into the chat box.
Adobe is bringing generative video and audio capabilities directly into Premiere Pro's timeline with a new Generative Media Tool, announced at IBC 2026. Editors can describe what they need and generate context-aware video clips or sound effects without leaving their project, with support for multiple AI models including Google Veo, Runway, and Luma. The update also includes a range of smarter audio tools and new AI features for After Effects.
Blackmagic Design has released DaVinci Resolve 21.1, a substantial update that brings AI assistant integration to the editing workflow alongside more than 100 new tools and controls. The update also expands the software's photo editing capabilities and adds support for a range of new camera formats and log profiles. Python scripting, previously available in the free version, has been moved exclusively to the Studio tier.
Runway has announced that the team behind Kinetix, a Paris-based research lab specializing in 3D human motion and physically-grounded video generation, is joining the company. The move is aimed at advancing Runway's work on world models for robotics and expanding its research footprint in Europe.
Adobe is reworking how video editors access AI generation tools inside Premiere Pro, bringing video, audio, and music generation directly into the editing timeline. The update centers on a new Generative Media tool that lets editors fill gaps in their projects without switching apps or breaking their flow. The underlying generators are not entirely new, but their integration into the timeline is a meaningful shift in how the tools are used in practice.
OpenAI has introduced ChatGPT Images 2.5, an updated image generation model designed to produce more personalized and polished results from user inputs like text prompts, sketches, and reference photos. The update focuses on better translating a user's intent into the final output. It represents an incremental but meaningful step forward in how ChatGPT handles visual creation tasks.
Google's Gemini app is testing a new visual feature called Immersive View within its Students section, offering an image-driven way to explore topics through interconnected nodes. The interface appears to let learners navigate subjects - from dinosaurs to molecules - in a branching, non-linear format. The feature has been spotted in early testing by TestingCatalog.
When a restaurant's Facebook post featuring obviously AI-generated food images drew criticism in the comments, a familiar counter-argument surfaced: traditional photography is manipulated too, so what's the difference? The claim deserves more scrutiny than it usually gets.
IndieWire's Brian Welk sat on the jury for the Reply AI Film Festival, screening six hours of generative AI short films ahead of the event's showcase in Venice. His reflections offer a grounded look at where AI filmmaking stands today - its recurring patterns, its limitations, and the creative choices that actually stand out.
Google has introduced an agentic video understanding capability for its Gemini Flash models that selectively loads only the video segments relevant to a given prompt, rather than processing entire videos at a flat rate of one frame per second. The approach reduces video token consumption by as much as 88%, making long-form video analysis significantly more efficient. This marks a shift in how large language models interact with video content - from passive ingestion to active, query-driven navig
