Google has added its new AI video generation model Veo 2 to YouTube Shorts, enabling creators to produce AI-generated video clips from text descriptions. As reported by Amanda Silberling for TechCrunch, the feature builds upon the existing Dream Screen capability, which previously only allowed AI-generated backgrounds. The new integration lets users create complete video sequences …
Adobe has released its Firefly Video Model for public beta testing, introducing AI-powered video generation tools that the company claims are trained exclusively on licensed content. The new service allows users to create videos from text descriptions or images through Adobe’s redesigned Firefly web application and Premiere Pro integration. The video generator produces 1080p clips …
ByteDance has developed an AI system that can generate realistic full-body videos from a single photograph. The new technology, called OmniHuman, can create videos of people speaking, singing, and moving naturally with matching gestures. As reported by Michael Nuñez, the system was trained on over 18,700 hours of human video data. OmniHuman combines multiple input …
Luma AI has released Ray2, its latest AI video generation model, offering improved motion quality and physics simulation in generated videos. According to reporting by Carl Franzen, the new model was trained with ten times more computing power than its predecessor. The San Francisco-based company’s CEO Amit Jain announced that Ray2 delivers faster and more …
Former Google CEO Eric Schmidt has founded a new AI startup called Hooglee, focusing on AI-powered video generation and social networking. According to Forbes reporter Sarah Emerson, the company aims to “democratize video creation with AI” and is currently funded by Schmidt’s family office, Hillspire. Sebastian Thrun, co-founder of Google’s Waymo, leads the project alongside …
Adobe Research and Hong Kong University of Science and Technology have developed TransPixar, an AI system that creates transparent visual effects for videos. As reported by Michael Nuñez in VentureBeat, the technology generates see-through elements like smoke and reflections that blend naturally into scenes. The system works with limited training data and uses a novel …
Nvidia has unveiled multiple new AI initiatives at CES 2025, centered around their Nemotron model families and Cosmos World Foundation Models. The company’s CEO Jensen Huang presented these developments during his opening keynote, introducing AI models designed to advance both enterprise and consumer applications. The Nemotron family includes language and vision models available as NIM …
Runway, a New York-based AI company, has introduced a new online platform connecting AI filmmakers with potential employers. According to an article by Shubham Sharma for VentureBeat, the network aims to help brands, agencies, and studios find specialized AI video talent. The platform already features dozens of independent artists and production houses, including members of …
Google DeepMind has announced Veo 2, its latest AI video generation model, positioning it as a direct competitor to OpenAI’s Sora. The new model is currently available through Google Labs’ VideoFX platform on a waitlist basis, with users required to apply through a Google Form for access. According to Google, Veo 2 can generate videos …
Meta has introduced a new open-source tool called Video Seal that adds invisible watermarks to AI-generated videos. According to Kyle Wiggers from TechCrunch, this development comes as deepfakes have increased fourfold worldwide from 2023 to 2024. The tool can embed hidden messages within videos to track their origins and is designed to withstand common editing …