Image and Video Generation
Generative image and video models, editing tools, creative workflows, media production, synthetic content, and visual AI product launches.
Genie 4 Lets Users Steer Generated Worlds as They Unfold
Google DeepMind presents Genie 4 as a world model built for continued interaction: users can move through generated environments, steer scenes with text prompts and see how they develop in real time. The company’s demonstrations show prompts changing an unfolding scene, from directing a crane toward a piano to adding events and characters to other settings. DeepMind also proposes virtual robot practice as a possible application, while describing access as a limited research preview.
GPT-6 Astra Extends Higgsfield’s AI Videos From One Minute to Over 10
Higgsfield says GPT-6 Astra has extended the videos it can generate from around one minute to more than 10, addressing what founder Alex Mashrabov calls one of creative AI’s hardest problems: maintaining consistency over longer work. He presents the gain as part of a broader effort to help smaller teams make more ambitious projects, alongside tools for producing images with readable text and working through 3D revisions.
Spatial Intelligence Extends AI Beyond Language Into Three-Dimensional Worlds
Fei-Fei Li argues that the next frontier in artificial intelligence is spatial intelligence: systems that can perceive and work with three-dimensional worlds, not just language and flat images. In a conversation with historian Stephen Kotkin, the Stanford computer scientist and World Labs co-founder connects that ambition to a broader question about how intelligence works—and says the development of powerful AI also demands truth-seeking, public responsibility and greater attention to teachers and families.
Bring Your Own Compute Could Make AI Apps Viable for Small Developers
OpenAI’s “Sign in with ChatGPT” could let apps use a customer’s existing AI allowance instead of paying model costs themselves, TBPN hosts John Coogan and Jordi Hays argue. They see the feature as a potential way to make compute-heavy products viable for small developers, but say it also raises a question of control: whether OpenAI is offering a useful integration or laying the groundwork for an app-store model that could leave developers with less leverage over customers and billing.
GPT Image 2.5 Splits Image Generation Between Speed and Precision
ElevenLabs’ review of OpenAI’s GPT Image 2.5 argues that the release is less a new capability jump than a clearer choice between speed and editing precision. Its Flare variant is positioned for faster, high-volume generation, while Sunburst is intended for reference-image fidelity and localized, multi-round edits; in one 2K test, both were faster than GPT Image 2, though Sunburst took longer than Flare.
Amazon Blocks Meta’s Muse to Defend Shopping and Advertising Control
TBPN hosts John Coogan and Jordi Hays argue that the commercial value of new AI video and shopping agents will depend less on raw model performance than on who controls the consumer interface. Coogan says ByteDance’s video advantage comes from its existing TikTok, CapCut and advertising distribution, while Hays casts Amazon’s block of Meta’s Muse as a defense of its shopping and advertising economics. They also report that Paramount’s settlement over its Warner Bros. Discovery acquisition keeps major production assets in California under a larger media owner.
Studio 4.0 Keeps AI-Generated Video Editable on the Timeline
ElevenLabs presents Studio 4.0 as an agentic video editor built around an editable project timeline rather than one-off media prompts. The company says users can generate video, images, voiceovers, music and sound effects within the same workspace, then revise shots, captions and audio alongside the rest of the edit. Its Studio Agent can assemble a first draft or handle tasks such as captioning, while leaving editors able to alter the work and hand it back to the agent.
AI-Generated Video Enters the Editable Project Timeline
ElevenLabs is positioning Studio 4.0 as an agentic video-editing workspace where generated video, images, voice, music and sound effects remain editable within the same project. The company argues that users can generate and revise shots by prompt, then work with them on a conventional timeline through frame-level controls, captions, comments and dubbing. Its Studio Agent is presented as a co-editor that can create a first draft or carry out tasks such as captioning, while leaving the editor in control of the project.
Flow Matching Turns Distribution Learning Into Velocity Prediction
Aritra Gosthipaty presents flow matching as a distribution-learning method that turns Gaussian noise into data by training a model to predict velocities along constructed paths between the two. In his introductory tutorial, each training image is paired with noise and connected by a simple straight-line interpolation, making the correct velocity available as a training target; generation then follows the learned local velocity field from fresh noise. The browser-based digit demo shows both the mechanism and its limits under compressed representations and simple sampling.
Claude Turns Product Links Into Editable AI Ad Workflows
ElevenLabs presents its MCP for Claude as a way to manage AI ad production through chat while retaining access to the underlying ElevenCreative Flows workflow. In a tutorial demonstrated by Alec Wilcock, users can start with a product link, approve stills and voice takes, revise motion or narration, and reformat a finished ad, while Flows exposes the separate image, video, voice and composition steps. The process still depends on user decisions—and on manual product details when a linked page cannot be retrieved.
MiniMax H3 Unifies Video, Image, and Audio References in One Generation
MiniMax argues that video generation’s separate tools for motion, subjects, frames and audio can be consolidated into H3, a model that takes text, image, video and audio references in a single generation. Presented by ElevenLabs in its ElevenCreative platform, H3 produces five- to 15-second clips with generated audio, timecoded multi-shot prompts and a 2K regeneration pass that retains the original instructions and references. H3 Max, built by fal from MiniMax’s published weights, trades that 2K option for a claimed roughly three-second generation time for a five-second 768p clip.
Infrastructure Hiring Is Delaying AI’s Broad Jobs Reckoning
TBPN hosts John Coogan and Jordi Hays argue that AI’s most meaningful advances will be the ones people can see operating in the world, not necessarily headline mathematical achievements such as OpenAI’s claimed Navier–Stokes proof. Coogan treats such proofs as evidence of model capability rather than an immediate engineering breakthrough, while pointing to computer-use agents, 3D generation and robotics as more tangible demonstrations. On jobs, he says current AI layoffs remain small relative to broader hiring tied to data centres, infrastructure and technical roles, postponing rather than disproving concerns about displacement.
GPT-Image-2.5 Splits Image Generation Between Control and Speed
OpenAI has introduced two GPT-Image-2.5 models for different image-production workflows: Sunburst, which it says offers sharper rendering, stronger prompt compliance and greater consistency across successive edits, and Flare, which it says generates images more than 50% faster than GPT-Image-2 at comparable quality. Both models support native transparent backgrounds and are available through the API, ChatGPT and Codex.
Gemini Omni Flash 1.1 Adds Start-End Frames and Video Extension
ElevenLabs presents Gemini Omni Flash 1.1 as a control-focused update to Google’s conversational video model, adding fixed start and end frames, a separate mode for extending uploaded footage, and lower-cost 360p testing. The company cautions that 1080p and 4K are upscaled exports from native 720p generations, while seamless extensions require users to select the dedicated Extend workflow and explicitly instruct the model to preserve continuity.
Generative Images Turn Location Scouts Into Campaign Concept Canvases
OpenAI’s marketing team argues that ChatGPT Images can move campaign exploration closer to the real-world site before a creative direction is chosen. Using a scouting photo of a Chicago billboard, the team first converted the angled facade into a straight-on design canvas, then generated competing concepts—from a brick wall opening onto a pastoral landscape to an L train emerging from the building—to assess them in context. The workflow is presented as a way to develop and compare more location-specific ideas before committing to a final composite.
Static Ad Localization Requires Copy-Only Edits and Language-Specific QA
ElevenLabs argues that static-ad localization can be automated without rebuilding creative, provided the model is tightly instructed to alter only customer-facing copy and preserve logos, brand names, typography, layout and imagery. Its tutorial shows how to build a reusable flow that creates language-specific versions from a single input ad, then uses an LLM check to flag translation and text-fit errors. For larger paid-media operations, the company positions its Ads Engine as the enterprise option for translating and distributing static and video creative across up to 90 languages.
Four Continuities Make the Fall-Through-Feed Effect Work
ElevenLabs’ tutorial argues that the “fall through the feed” effect is an editing illusion built on four continuities: a consistent subject and falling pose, scenes that begin empty and end with the subject exiting below frame, and identical upward motion for footage and social-media interface. Its workflow uses Nano Banana 2 and GPT Image 2 to establish reference and style frames, Seedance 2.0 to animate the falls, and Premiere Pro to synchronize the posts into a continuous scroll.
Apple Cuts Vision Pro Teams to Expand Siri AI Infrastructure
Apple is cutting more than 200 jobs across Vision Pro, Siri and Intelligent Systems Experiences as it redirects resources toward AI, Bloomberg’s Mark Gurman reports. He characterizes the Vision Pro reductions as a conventional retrenchment—including the elimination of its gaming-initiatives team and less in-house immersive-video production—while the software cuts are intended to make room for engineers building Siri’s new AI infrastructure, voice assistant and upgraded Apple Intelligence.
ElevenLabs Adds Agent Monitoring and Context-Preserving Voice Tools
ElevenLabs’ monthly changelog argues that its latest releases are less about adding generation models than about making AI voice workflows more controllable in production. The company has introduced Spotlight to identify recurring problems in live agent conversations, Character Casting and consistent vocals to standardize creative choices, and API updates intended to preserve performance in dubbing and structure in real-time transcription.
AI Workflows Generate Localized Thumbnails From One Master Design
ElevenLabs argues that localizing YouTube thumbnails is a design problem as much as a translation task: foreign-language headlines must fit the original composition without altering logos, faces, backgrounds or visual hierarchy. Its ElevenCreative Flows tutorial shows creators how to generate language-specific versions from one master image, with each language branch verified by an LLM that checks the headline’s translation and meaning. The company presents the resulting template as a repeatable alternative to redesigning each thumbnail manually.
AI Exposes Which Software Moats Extend Beyond Code
John Coogan and Jordi Hays argue that AI has weakened software businesses whose main value is readily reproducible code, but has not erased the value of companies built on distribution, customer relationships, operational infrastructure and embedded workflows. They use Chegg as the clearest case of direct displacement, while arguing that platforms such as Shopify, Twilio and Roblox retain harder-to-recreate assets. The discussion also examines how remote hiring can be exploited by North Korean IT workers using stolen identities and U.S.-hosted devices, and why high compensation may not keep AI researchers from leaving large labs to found companies.
FLUX 3 Launches Multimodal Video Generation With Native Audio
Black Forest Labs presents FLUX 3 as its first video model, trained jointly on images, video and audio to generate up to 20-second clips with dialogue, sound effects and ambience created alongside the frames. The source argues that its Self-Flow training approach improves semantic understanding without a separate vision model, underpinning claimed gains in motion, faces, hands and in-scene text. It positions video continuation and low-cost Draft mode as the most practical workflow features, while noting that the preview release lacks editing and reference support.
Character Reference Sheets Make AI Film Workflows Reusable
ElevenLabs’ Alec Wilcock argues that AI short films should be built around continuity rather than motion: establish the character, visual style and composition in still images before spending credits on video. His *Little Wanderer* workflow uses a reusable character reference sheet, narration-led story beats, and start and end frames to constrain each shot, then assembles and trims the results in Studio. The node-based Flows canvas, he says, makes the project reusable by allowing an upstream character change to regenerate the same film structure with a new protagonist.
Seedance 2.5 Extends AI Video Generation to 30 Continuous Seconds
ElevenLabs presents ByteDance’s Seedance 2.5 as an AI video model built to reduce the stitching and full-shot rerolls required in earlier workflows. Compared with Seedance 2.0, it generates continuous 4K clips of up to 30 seconds, accepts 50 reference assets rather than 12, and adds 3D-reference guidance and region-level editing. The company argues that these changes give creators more control over continuity, framing and corrections without having to regenerate an otherwise usable shot.