Latest news with #HenryDaubrez
Gizmodo
3 days ago
- Entertainment
- Gizmodo
Bad News: Google's Veo 3 Can Make VR Slop, Too
Just when we thought the AI slop fest was over, Google pulls us right back in. First, we had YouTube slop, then video game slop, and then we had Michael Bay slop. And just in case you weren't already slopped full of slop juice squeezed straight from the slop teat of Veo 3, Google's latest AI video generator model, you all had to go ahead and invent new kinds of AI slop that make Sloppy Joe himself say, 'I think that's too much slop for me, fam.' Introducing: 360-degree video slop made by Google Veo 3. Here's a collection of a bunch of the clips I created with VEO 3 to test out it's ability to generate 360° video. I'll post a link below to a VR ready youtube video so you can test it on your own VR headsets. — Martin Nebelong (@MartinNebelong) June 6, 2025 That's right, your poor, innocent VR content isn't safe from Veo 3's generative abilities either. While I haven't had a chance to actually view this content in VR, creating it couldn't be simpler. Per Henry Daubrez on X, who initially discovered the trick, all you have to do is add 'make it 360 degrees' to your Veo 3 prompt to generate video that can later be viewed in VR. Well, almost. There's a little bit of fussing with the metadata afterwards, too, in order to get everything working right. In a post on X, Daubrez says, '…the next step is to inject the right metadata in your file so you can play it as an actual 360 video. I tried a few available solutions, but in the end, using the Terminal was the only one [that] actually [worked] for me with ExifTool… Once it's saved with the right metadata, it will be recognized as an actual 360/VR video, meaning you can just play it in VLC and drag your mouse to look around.' 🤯 How to generate VR/ 360° videos directly with VEO3 Alright, I just randomly stumbled on that very neat trick: If you prompt for a 360° video in VEO3 (like literally write "360°" ) it can generate a Monoscopic 360 video, then the next step is to inject the right metadata in… — Henry Daubrez 🌸💀 (@henrydaubrez) May 30, 2025 But that's pretty much it: prompt Veo 3 and then slightly alter the metadata, and boom, you've got an AI-generated video that can be played back in VR. There are some quirks, of course, like the addition of black bars around some of the generated content. But for the most part, Veo 3 works about as well with 360-degree content as it does with anything else prompters have thrown at it, especially, as Daubrez mentions, when you consider that this likely isn't even a planned feature of Veo 3. If you want to watch some of Veo 3's ad hoc VR video for yourself, there's already some on YouTube for your viewing pleasure (or displeasure, depending on what your relationship to AI is). Just like with any Veo 3 application, there's big potential for slop here, but I'll be honest, I'm going to give this one a bit of a pass. I don't think VR video is quite at the point of high art yet (no offense, VR creators), and, to be honest, I kind of like the idea of being able to generate VR experiences that don't exist yet, especially because the VR catalog is still somewhat limited. I'm sure I'll end up eating those words sooner rather than later, and just like a Sloppy Joe, it might eventually erode your body from the inside out—but hey, there's a time and a place for junk food, so have fun while you can, folks.
Time of India
21-05-2025
- Business
- Time of India
Google launches AI video creator Flow with Veo 3
Google unveiled its new AI-powered video generator, Flow, at its developers' conference on Tuesday. It is the latest iteration of VideoFX, a Google Labs experiment launched last year, and can generate video and audio elements. Google Flow uses its video model Veo 3 , text-to-image model Imagen and AI assistant Gemini to generate subjects, scenes and clips from text prompts. These can be pieced together into videos as per the creator's discretion. Flow allows camera control with the ability to control the motion, angles and perspectives when creating a video. Users can edit and extend the frame to reveal more elements or transition to the next scene. The AI video tool allows users to manage and organise all created elements, dubbed 'ingredients', and prompts used to make them Google has also added Flow TV, which gives exact prompts and techniques for clips, helping creators learn new styles. Live Events The company has collaborated with filmmakers Dave Clark, Henry Daubrez and Junie Lau to assess how Flow can be integrated into their workflow and improve it using their insights. Discover the stories of your interest Blockchain 5 Stories Cyber-safety 7 Stories Fintech 9 Stories E-comm 9 Stories ML 8 Stories Edtech 6 Stories Google Flow is available to Google AI Pro and Google AI Ultra subscribers in the US, and will be rolled out to more countries soon, the internet major said. Google AI Pro comes with key Flow features and 100 generations per month. The Google AI Ultra gives users the highest usage limits and early access to Veo 3 with native audio generation, bringing environmental sounds and character dialogue directly into video creation. Also Read: Key takeaways from Google I/O 2025: Gemini, Search in focus
India Today
20-05-2025
- Entertainment
- India Today
Google I/O 2025: Flow is AI video generator tuned for filmmaking, Google says it is working with Hollywood
Flow, a new AI-powered tool built for filmmaking and creative video production, has been introduced at Google I/O 2025. The platform brings together some of Google's most advanced AI models — Veo, Imagen and Gemini — and is designed to help creators produce high-quality cinematic scenes with minimal effort. It offers a way to bring ideas to life quickly, without the need for large teams or heavy editing tools. According to Google, Flow is built 'by and for creatives' and is already being used by a small group of filmmakers to explore what AI can bring to the production process. Image: Google/ YouTube advertisementEarly adopters include award-winning filmmakers like Dave Clark, who used Flow to develop his short film Freelancers, a story about two estranged adopted brothers. Henry Daubrez, known for blending tech and art, created Kitsune with Veo 2 and is now working on Electric Pink. Junie Lau, a director exploring digital narratives, is using Flow for Dear Stranger, a film about love across parallel combines video generation, scene editing and asset control into one workspace. It supports different ways of creating videos, including starting from text descriptions or building shots around existing visuals. Users can upload characters, objects or scene references to help guide the AI and keep visuals consistent across multiple clips. They can also turn a still image from one scene into the basis for another. These features aim to make storytelling feel more connected, especially for those working on longer or more detailed projects. Image: Google/ YouTube advertisementOne of the main highlights is Scenebuilder, which helps creators edit and expand their shots. It allows transitions to feel natural and actions to flow smoothly from one moment to the next. Flow also includes camera controls, giving users more say over angles, motion and perspectives. This puts more creative direction in the hands of the user, rather than relying completely on the AI's automatic help manage larger projects, Flow includes tools for organising assets and prompts. Google has also introduced something called Flow TV — a showcase of clips created with Flow, where users can view shared projects, see the prompts used and learn how different effects were is currently available to subscribers of Google's AI Pro and AI Ultra plans in the US. The Pro plan offers access to key features and 100 generations a month, while Ultra users get higher limits and early access to Veo 3, which supports environmental sounds and character Flow is still in its early stages, Google says it wants the tool to become a serious part of how stories are told in future — across film, advertising, education and more. More updates are expected in the coming months as the tool rolls out to a broader group of users.
Engadget
20-05-2025
- Engadget
Google's new filmmaking tool Flow adds editing tools and some consistency to AI-generated video
Your Yahoo privacy setting is blocking social media and third-party content You can Allow your personal information to be shared and sold. Something went wrong. Try again. You can update your choice anytime by going to your privacy controls, which are linked to throughout our sites and apps. This page will now refresh. At I/O today, Google pitched creators on a new app for "AI filmmaking": Flow. Combining all of Google's recent announcements and developments across AI-powered services, including Veo (video), Imagen (images) and Gemini, the company bills Flow as a storytelling aid 'built with creatives.' If it sounds familiar, this is the advanced version of VideoFX, previously a Google Labs experiment. It says it's aimed at helping storytellers to explore ideas and create clips and scenes, almost like storyboards and sketches in motion. Google's generally impressive Veo 2 model seems to form the core of Flow, able to extend footage and create video that 'excel(s) at physics and realism', although I'm not sure many agree with that.. You can use Gemini's natural language skills to construct and tweak the video output, and creatives can pull in their own assets or create things with Imagen through simple text input. What's notable is the ability to integrate your creations and scenes into different clips and scenes with consistency. While the early demo footage we saw was impressive, it still had a not-so-faint AI-slop aroma. There are further film-making tools, too. Flow will also feature direct control over the movement of your 'camera', and even choose camera angles. You can also edit and extend shots, adding different transitions between AI-generated videos. Creating video with Veo is often a piecemeal process, but Flow will have its own asset management system to organize assets and even your prompts. These richer controls and editing abilities could make for more compelling creations in time. Let's not forget: It's been less than a year since that very weird Toys R'Us ad. Google buddied up with several notable filmmakers to attempt to legitimize collaborate on these still-early steps into AI video creation, including Dave Clark, Henry Daubrez and Junie Lau. It says it offered creatives early access to the tools, and folded in their insights and feedback into what is now called Flow. Flow is now available to AI Pro and AI Ultra subscribers in the US, and will roll out to other countries soon. Pro users will get Flow tools outlined so far and 100 generations each month. With the Ultra sub, you'll get unlimited generation and early access to Veo 3, with native audio generation.
Tom's Guide
20-05-2025
- Entertainment
- Tom's Guide
Google Veo 3 and Flow: The future of AI filmmaking is here — here's how it works
Google is taking a major leap into AI filmmaking with the launch of Veo 3 and Flow, powerful new video tools designed to help creatives turn their ideas into cinematic scenes with a single prompt. Flow is custom-built for Google's top AI models: Veo (for video generation), Gemini (for prompting and language), and Imagen (for text-to-image capabilities). Together, they make it possible to generate rich, visually stunning narratives without needing a professional film crew. Flow is Google's first AI filmmaking tool built specifically for creatives. While tools like Runway and Pika Labs offer short-form generative video, Flow stands out with its deep integration of Google's language and vision models — letting users craft entire scenes with characters, dialogue, and camera movement in one place. You can describe a scene in everyday language, and Flow will generate a cinematic clip using Veo's physics-accurate rendering engine. Gemini helps interpret prompts intuitively, and Imagen can create characters or elements to include in your video. Users can now go beyond static clips to create scenes, add new angles, edit transitions and maintain visual consistency across shots. Get instant access to breaking news, the hottest reviews, great deals and helpful tips. You can also bring in your own assets and reuse them in new scenes. Google has collaborated with a few early adopters to test Flow in the real world: Dave Clark created shorts like Battalion and NinjaPunk using AI. Henry Daubrez is using Veo 2 to tell emotional sci-fi stories. Junie Lau explores identity and relationships in films like Dear Stranger. Flow is available now to subscribers of Google AI Pro and Google AI Ultra. AI Pro users get 100 generations per month and access to Veo 2, previously part of Google's latest rollout for Gemini Advanced users. This tool lets you generate 8-second, 720p cinematic videos using a single prompt. Although Veo 2 does not offer sound like Veo 3, it gives you mini-films that are 8 seconds long. Released April 15, the feature quietly appeared as a dropdown option in users get early access to Veo 3, including support for native audio, environmental sounds, and character dialogue. Flow is still in its early stages, but it could be the start of a new era in storytelling, opening doors for creators of all skill levels.
