gen‑ai.news

The pulse of generative image & video AI.

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.

Archive

Anyone can create a personal avatar of themselves in Google Vids, at no cost.
Video

Anyone can create a personal avatar of themselves in Google Vids, at no cost.

Google has opened up personal avatar creation in Google Vids to all users at no cost. Using a selfie and a short voice recording, anyone can build a digital likeness capable of narrating videos on their behalf. The feature lowers the barrier to producing on-camera content without requiring recording equipment or studio time.

Building Visual Intelligence — Andreas Blattmann & Dustin Podell, Black Forest Labs
Multimodal

Building Visual Intelligence — Andreas Blattmann & Dustin Podell, Black Forest Labs

Andreas Blattmann and Dustin Podell of Black Forest Labs lay out their thinking on how generative models trained on visual data - pixels, motion, and sound - could serve as a meaningful path toward general intelligence. The conversation digs into the technical and philosophical foundations behind the lab's approach to building visual AI systems. It offers a grounded look at why the founders believe perception-driven learning is worth pursuing at the frontier.

Apple is testing daily usage limits for more complex Siri AI interactions
Image

Apple is testing daily usage limits for more complex Siri AI interactions

Apple is testing daily usage limits on more advanced Siri and Apple Intelligence features in the latest developer betas of iOS, iPadOS, and macOS 27.3. Cloud-dependent tasks like image generation and multi-step personal requests would be capped, while basic Siri commands remain free and unlimited. The move signals a possible shift toward tiered access for computationally intensive AI features.

OpenAI wants to stop deepfakes from overwhelming child abuse tiplines
Image

OpenAI wants to stop deepfakes from overwhelming child abuse tiplines

OpenAI has announced a classifier designed to help child sexual abuse material investigators identify harmful imagery more efficiently, including content that is AI-generated. The tool will be made available free of charge to vetted organizations working in this space. The move comes as pressure mounts on AI developers to take more concrete steps toward safety.

A Quick Look at How Adobe’s New AI Assistant Could Streamline Your Workflows in Premiere
Video

A Quick Look at How Adobe’s New AI Assistant Could Streamline Your Workflows in Premiere

Adobe introduced a conversational AI assistant for Premiere Pro at its annual MAX conference, letting editors use natural language prompts to handle organizational and assembly tasks directly inside the application. The feature draws on Firefly generative credits, meaning it carries an ongoing cost tied to usage. Whether it meaningfully reduces repetitive work for real-world editing projects remains to be seen outside of controlled demos.

Everything You Need to Know About Adobe Premiere 27.0 and Its Latest Improvements
Video

Everything You Need to Know About Adobe Premiere 27.0 and Its Latest Improvements

Adobe has released Premiere Pro 27.0 following Adobe MAX 2026, bringing a dedicated Color Mode workspace, several AI-driven audio tools, and a range of workflow improvements for video editors. The update also introduces new effects, HSL masking for color work, and native support for NVIDIA RTX Spark on Windows on ARM. Here is a breakdown of what has changed and what it means for editors day to day.

You can now generate and edit GIFs with ChatGPT - here's how
Image

You can now generate and edit GIFs with ChatGPT - here's how

OpenAI has added GIF generation and editing to ChatGPT, giving users a way to create short animated images directly within the chat interface. The feature expands on the platform's existing image capabilities, extending them into the animated format. Here is what you need to know to get started.

Maket launches floor and wall textures from text or images
Image

Maket launches floor and wall textures from text or images

Maket, an AI-assisted architectural design tool, has added the ability to generate floor and wall textures directly from text prompts or reference images. The feature gives designers a faster way to explore material options within their existing workflow. It represents a natural expansion of Maket's generative toolset into the domain of surface and finish design.

Video

Best AI Video Generation Models in 2026: Elo, Price per Second, Open Weights

The AI video generation landscape has shifted considerably over the past year, with native audio, longer clip lengths, and open-weights models now firmly part of the competitive field. A November 2026 ranking from Artificial Analysis's blind human-preference Elo arena pairs quality scores with API pricing to give a clearer picture of where each model stands. The result is a leaderboard that looks notably different from what it did in late 2025.

AI Ambition: ArtCraft Cloned Photoshop and Now Wants to "Rebuild Everything"
Image

AI Ambition: ArtCraft Cloned Photoshop and Now Wants to "Rebuild Everything"

ArtCraft made waves by using AI to build an open-source reimagining of Photoshop, and CEO Brandon Thomas says that is only the beginning. The company's broader ambition is to challenge the closed, proprietary systems that dominate creative software and the web. It is a bold long-term goal, rooted in the idea that AI can lower the barrier to rebuilding complex software from scratch.

5 new Google Flow Tools designed by visual artists
Video

5 new Google Flow Tools designed by visual artists

Google has added five new tools to Flow, its AI-powered filmmaking platform, developed with input from working filmmakers and visual artists. The additions are aimed at giving creators more precise control over how their stories are visualized and produced. Each tool addresses a specific stage or challenge in the visual storytelling process.

Runway News | Closing the Gap Between Policy and Practice
Video

Runway News | Closing the Gap Between Policy and Practice

Runway has updated its content moderation policies to permit a broader range of dramatic and genre fiction content - including sword fights, shootouts, and horror - while keeping firm limits around genuine harm. The changes reflect an effort to bring the platform's written rules closer in line with what its systems actually allow in practice. Users can also now flag cases where moderation gets it wrong.

Premiere on PC Gets a Boost as Adobe and Microsoft Announce Expansion of Partnership
Video

Premiere on PC Gets a Boost as Adobe and Microsoft Announce Expansion of Partnership

Adobe and Microsoft have deepened their partnership to bring better-optimized versions of Photoshop, Premiere, After Effects, and Substance 3D Painter to high-performance Windows PCs. The expansion also includes Adobe Express capabilities coming to Microsoft Photos, with a preview for Windows Insiders expected in December. The move is tied to a separate Adobe-NVIDIA collaboration centered on RTX Spark-powered hardware.

Image

Phota Labs uses AI to turn everyday photos into professional-looking shots

Phota Labs is a new AI-powered service that automatically processes ordinary photos into polished, professional-looking images without requiring users to touch an editing tool. Rather than layering more manual controls onto an already crowded market, the company focuses on automating the entire editing pipeline. The goal is to make quality photo output accessible to people who have no background in photography or post-processing.

Avid Moves Into the AI Age With Its Ready to Play for Avid Media Composer
Video

Avid Moves Into the AI Age With Its Ready to Play for Avid Media Composer

Avid has launched Ready to Play, a suite of AI-assisted tools built into Media Composer using Google Gemini. The update introduces three core capabilities - creating, analyzing, and modifying video - designed to help editors maintain momentum without ceding creative control. It is available now as a free add-on for existing Media Composer subscribers.

Customer Tried to Scam LA Pizza Shop With AI Image
Image

Customer Tried to Scam LA Pizza Shop With AI Image

A customer at a Los Angeles pizza shop attempted to use an AI-edited photo of their order to claim a refund, but the scheme did not succeed. The incident highlights a growing concern for small businesses as image generation and editing tools become more accessible. It is a early real-world example of AI-fabricated evidence being used in a consumer dispute.

What Is MAX Sneaks? Your First Look at Tools That Don’t Exist Yet
Multimodal

What Is MAX Sneaks? Your First Look at Tools That Don’t Exist Yet

Adobe MAX Sneaks is an annual event where Adobe researchers demo experimental technology that has not yet made it into any product. Some of these demos eventually become familiar tools in Premiere, After Effects, or Photoshop - others never ship at all. This year's Sneaks airs Wednesday, November 11, and is free to watch online.

Adobe’s AI experiments let you walk around in photos and interview your characters
Multimodal

Adobe’s AI experiments let you walk around in photos and interview your characters

Adobe's annual Max conference has brought a fresh batch of experimental features, including tools that convert flat photos into navigable 3D scenes, let creators shape AI characters through conversation, and simplify photo editing to a copy-and-paste workflow. These "Sneaks" projects offer a glimpse into where Adobe's generative AI research is heading. None are shipping products yet, but they reflect the direction of the company's broader creative toolset.

Video

MBZUAI’s IFM Releases PAN 2, an Open 29B World Model for Physical AI

MBZUAI's Institute of Foundation Models has released PAN 2, an open-weight world model designed for physical AI applications. The system pairs a language model planner with a 29-billion-parameter diffusion transformer to simulate the visual outcomes of actions as video clips of up to 20 seconds. It is released under the permissive Apache 2.0 license, making it freely available for research and commercial use.

VSCO Updates Its Policy to Explicitly State It Won’t Train AI on Your Photos
Image

VSCO Updates Its Policy to Explicitly State It Won’t Train AI on Your Photos

VSCO has updated its Terms of Use to explicitly state that it does not and will not use user photos to train generative AI or machine learning models. The move comes months after vague policy language raised concerns among photographers and creators on the platform. The clarification offers a clearer commitment than the previous wording provided.

Tom Hanks Played Five Characters in This 2004 Christmas Movie
Multimodal

Tom Hanks Played Five Characters in This 2004 Christmas Movie

The Polar Express, Robert Zemeckis's 2004 performance-capture film, is back in seasonal rotation - and it remains one of the more technically unusual productions of its era. Tom Hanks played five distinct characters across 38 days of work, a casting choice that was rooted in story logic as much as technical curiosity. Here is a closer look at how that decision came together and what it meant for the actors involved.

MiniMax H3-Image: Bringing 4K Image Generation into the 10-Second Era - MiniMax Research
Image

MiniMax H3-Image: Bringing 4K Image Generation into the 10-Second Era - MiniMax Research

MiniMax has released H3-Image, an open-weight image generation model capable of producing 4K images in roughly 10 seconds. The model supports text-to-image generation, reference-based generation, and image editing within a single architecture. Built on MiniMax's H3 foundation, it marks the company's entry into the open-weight visual generation space.

Introducing the Multimodal Knowledge Agent benchmark
Multimodal

Introducing the Multimodal Knowledge Agent benchmark

Google has introduced the Multimodal Knowledge Agent (MKA) benchmark, a new evaluation framework designed to test how AI agents reason through visually complex, multimodal tasks. Unlike simpler benchmarks, MKA focuses on the kind of layered reasoning required when an agent must draw on both visual and textual information simultaneously. The release signals growing interest in more rigorous, real-world testing standards for multimodal AI systems.

Adobe is going all in on agentic AI
Multimodal

Adobe is going all in on agentic AI

At its Max conference in Miami, Adobe outlined a broad push toward agentic AI, positioning chatbots and autonomous agents as potential collaborators in creative workflows. New features span Firefly, Creative Cloud, and third-party integrations - pointing to a future where repetitive design tasks can run largely on their own. The announcements signal a meaningful shift in how Adobe imagines its tools being used day to day.

Instagram’s Effect Builder makes new filters from AI prompts
Image

Instagram’s Effect Builder makes new filters from AI prompts

Instagram has launched Effect Builder, a tool that lets US users create custom Stories filters by describing them in plain text prompts. The feature also accepts style reference images and allows iterative refinements through follow-up prompts. It is available now for users aged 18 and over in the United States.

How to Turn Your Live-Action Short Into a Stylized Rotoscope-Animated Film
Video

How to Turn Your Live-Action Short Into a Stylized Rotoscope-Animated Film

GIANTS, a five-minute animated short screening at this year's Austin Film Festival, began as a live-action shoot in 2013 before filmmaker Nate Bayless transformed it into a stylized rotoscope-animated film over a decade later. The project is a case study in patience, creative reinvention, and the particular appeal of rotoscoping as a medium that sits between live-action and animation. No Film School spoke with Bayless about the film's long journey and what finally brought it to the screen.

Adobe MAX Kicks Off This Week as Company Shares Stats on Accelerating AI Use
Multimodal

Adobe MAX Kicks Off This Week as Company Shares Stats on Accelerating AI Use

Adobe MAX kicks off this week in Miami, and ahead of the conference the company has released its 2026 Creators' Toolkit Report, surveying over 2,000 US creators on how AI is shaping their workflows. The data shows broad adoption, with 78% of creators using AI tools reporting accelerated business or audience growth. Major announcements about AI integrations across Creative Cloud are expected throughout the week.

Disney and Adobe are building generative AI tools together
Multimodal

Disney and Adobe are building generative AI tools together

Disney and Adobe have announced a multiyear partnership to develop proprietary generative AI models tailored to Disney's creative and production needs. The collaboration, revealed at Adobe's MAX conference, spans properties from theme parks and cruise lines to ESPN content. The models are described as "artist-led," with a focus on responsible AI development.

More Realistic Images More Stable Editing Across 100 Rounds Introducing Seedream 5 5
Image

More Realistic Images More Stable Editing Across 100 Rounds Introducing Seedream 5 5

ByteDance has released Seedream 5.5, an update to its generative image model that focuses on two areas: improved photorealism and more consistent multi-round editing. The model claims stable output across up to 100 rounds of iterative editing, a significant step for workflows that require repeated refinement without drift.

Generate longer AI videos with Omni 1.2 Flash in Google Vids at no cost.
Video

Generate longer AI videos with Omni 1.2 Flash in Google Vids at no cost.

Google has updated its Vids app with the Omni 1.2 Flash model, allowing users to generate longer AI video clips of up to 15 seconds at no cost. The update also brings improved consistency across scenes, making it easier to produce cohesive video content. This marks a meaningful step forward in Google's effort to integrate generative video tools into its Workspace productivity suite.

New NVIDIA Cosmos 3 Open Models for Interactive World Simulation
Video

New NVIDIA Cosmos 3 Open Models for Interactive World Simulation

NVIDIA has released Cosmos 3, a new set of open models designed for interactive world simulation. The models are hosted on Hugging Face and represent a step forward in physically grounded, controllable video generation for robotics and autonomous systems research.

AI Movie ‘Gods Don’t Give Gifts’ Gets Serious with AI-Generated Grimes Cameo, Times Square Marketing Push, Oscar Screenings
Video

AI Movie ‘Gods Don’t Give Gifts’ Gets Serious with AI-Generated Grimes Cameo, Times Square Marketing Push, Oscar Screenings

An AI-generated feature film called "Gods Don't Give Gifts" is mounting a surprisingly serious awards campaign, complete with an AI-generated Grimes cameo, Times Square advertising, and official Oscar qualifying screenings. Creator Gossip Goblin argues the project deserves to be taken on its own terms rather than dismissed as a publicity stunt. The film is shaping up as one of the more visible tests of how the industry will respond to fully AI-generated feature content.

Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips
Video

Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips

Google has updated its Gemini Omni 1.2 Flash model with native video generation support, extending clip length to 15 seconds and introducing editing capabilities alongside improved consistency. The release also comes with a 30% reduction in pricing, making it a more accessible option for developers building video-focused applications.

Real-Time Video at Batch Size One | Runway Research
Video

Real-Time Video at Batch Size One | Runway Research

Runway has detailed how it serves its 57-billion-parameter video model - the one powering Runway Characters - at 24 frames per second for live, interactive conversation. The engineering work cuts the hardware requirement in half, from eight H100 GPUs down to four. The post offers a rare look at the infrastructure tradeoffs involved in running large generative video models at real-time latency.

Introducing Images 2.6
Image

Introducing Images 2.6

OpenAI has updated its image generation system to Images 2.6, adding faster output, GIF creation, and more precise editing tools. The update rolls out across ChatGPT, Codex, and the API, with new controls available to developers. It marks a steady incremental step in OpenAI's image tooling rather than a wholesale overhaul.

Those Jeff Bezos hair transplant photos are very fake
Image

Those Jeff Bezos hair transplant photos are very fake

Edited photos of Jeff Bezos and actor Jason Statham depicting both men with full heads of hair have been circulating on X, Threads, and Bluesky. The images are fabricated - produced through photo editing, AI-assisted or otherwise - and do not reflect any real change in either man's appearance. The Verge looked into the spread of these posts and found them appearing frequently enough to reach multiple members of their own team through social feeds.

AI inference startup Fal doubles its valuation to $16B as demand surges
Multimodal

AI inference startup Fal doubles its valuation to $16B as demand surges

Fal, an AI inference startup focused on generative media workloads, has raised $1.3 billion in a new funding round led by Bessemer Venture Partners, doubling its valuation to $16 billion. The five-year-old company has emerged as a key piece of infrastructure for developers building on top of image and video generation models. The raise reflects continued investor appetite for the compute and serving layer underneath generative AI applications.

Photographer Exposes AI-Generated Images in Another Photographer’s Portfolio
Image

Photographer Exposes AI-Generated Images in Another Photographer’s Portfolio

A photographer has called out a fellow photographer for allegedly passing off AI-generated images as genuine photographs in their portfolio, with the dispute centered on images of Whitehaven, a historic harbor town on the Cumbrian coast of England. The case highlights growing tensions within the photography community as AI image generation becomes increasingly convincing. It raises difficult questions about disclosure, authenticity, and professional ethics in an era when synthetic imagery can be

Adobe Expands Music Options in Premiere Mobile With Major Music Group Partnerships
Video

Adobe Expands Music Options in Premiere Mobile With Major Music Group Partnerships

Adobe has announced partnerships with Universal Music Group and Warner Music Group to bring licensed music from major artists into Adobe Premiere mobile. The move gives mobile video editors access to familiar tracks for use in their projects, with new browsing and editing tools to match. Tracks will be available for personal, non-commercial use when the feature rolls out.

AI-Generated Product Photos Are Putting Off Online Shoppers, Study Finds
Image

AI-Generated Product Photos Are Putting Off Online Shoppers, Study Finds

A new study from e-commerce UX research organization Baymard finds that a majority of U.S. online shoppers feel less confident purchasing a product when its photos appear to be AI-generated. The findings raise questions about how retailers should approach AI image tools as they become more accessible and widely used in product photography workflows.

Google takes Dreambeans to India in bid to bring AI-generated personal stories to the masses
Image

Google takes Dreambeans to India in bid to bring AI-generated personal stories to the masses

Google has expanded Dreambeans, its AI-powered personal storytelling experiment, to India with support for 13 Indian languages. The move signals Google's interest in bringing generative AI narrative tools to one of the world's largest and most linguistically diverse markets. It marks one of the broader regional rollouts for the product since its initial launch.

Runway News | Runway Dev is in Claude Code, Codex and Cursor
Video

Runway News | Runway Dev is in Claude Code, Codex and Cursor

Runway has released Dev plugins for three popular coding environments - Claude Code, OpenAI Codex, and Cursor - allowing developers to access Runway's generative media API directly from their editor. The integration lets coding agents build and invoke video and image generation features without leaving the development workflow. It is a practical step toward making generative media capabilities a routine part of software projects.

Google testing Comic Artifacts for Gemini Notebook
Image

Google testing Comic Artifacts for Gemini Notebook

Google is quietly testing a Comics artifact feature inside Gemini Notebook that would let users generate comic-style visuals directly within the tool. The feature appears to offer four distinct visual styles along with controls for language and page orientation, though no release date has been announced.

Adobe is testing how well AI agents can use editing tools like a Photoshop professional would
Image

Adobe is testing how well AI agents can use editing tools like a Photoshop professional would

Adobe Research and UC San Diego have developed EditAgent, an AI system that approaches image editing by selecting specialized tools for each task - much as a skilled Photoshop user would. Rather than repeatedly applying a single general-purpose model, it delegates decisions to a language model that evaluates results using measured image data. The trade-off is significant: the approach demands roughly ten times the compute of simpler methods.

Google wants video AI to understand what people need as they work
Video

Google wants video AI to understand what people need as they work

Google researchers have built StreamVibe, a video AI agent designed to observe people doing hands-on tasks and offer assistance only at the moments it is actually needed. A new benchmark reveals that current models struggle significantly with this timing problem, especially as videos grow longer and errors accumulate.

Meta quietly launches an AI fashion app for virtually trying on clothes
Image

Meta quietly launches an AI fashion app for virtually trying on clothes

Meta has quietly rolled out a new AI-powered fashion app called Style Sketch in three Southeast Asian markets - Indonesia, Singapore, and Thailand. The app allows users to virtually try on clothing using generative AI. The limited regional launch suggests Meta is testing the waters before any broader rollout.

Pika-Labs releases Pika-H3-Flex open weights on Hugging Face
Video

Pika-Labs releases Pika-H3-Flex open weights on Hugging Face

Pika Labs has released Pika-H3-Flex as open weights on Hugging Face, making its image-to-video model publicly available for local inference. The model generates video with synchronized audio in six sampling steps and supports up to 12 reference inputs for precise, reference-guided control. Native output runs at 480p or 768p locally, with higher resolutions available through Pika's hosted API.