vff
vff
NewsTrending

Google Launches Gemini Omni for AI-Powered Video Generation and Editing

Google Deepmind
Read original
Share
Google Launches Gemini Omni for AI-Powered Video Generation and Editing

Google DeepMind has introduced Gemini Omni, a multimodal model that generates and edits video from mixed inputs including images, audio, video, and text. The first model in the family, Gemini Omni Flash, is rolling out to the Gemini app, Google Flow, and YouTube Shorts with the ability to edit videos through natural language conversation while maintaining character consistency and physical coherence across multiple turns. Future versions will support additional output modalities like image and audio generation.

Google DeepMind has introduced Gemini Omni, a multimodal model that generates and edits video from mixed inputs including images, audio, video, and text. The first model in the family, Gemini Omni Flash, is rolling out to the Gemini app, Google Flow, and YouTube Shorts with the ability to edit videos through natural language conversation while maintaining character consistency and physical coherence across multiple turns. Future versions will support additional output modalities like image and audio generation.

  • Gemini Omni Flash enables video generation and editing from mixed input modalities (text, image, audio, video)
  • Users can edit videos conversationally with natural language, with edits building on previous instructions while maintaining scene consistency
  • Initial rollout targets Gemini app, Google Flow, and YouTube Shorts, with image and audio output modalities planned for future releases
  • The model grounds video generation in Gemini's real-world knowledge and allows users to transform existing footage or create entirely new content

Gemini Omni represents a significant step in multimodal AI capability, moving beyond text-to-image generation into video creation and editing. This consolidates reasoning and creative generation into a single model, which could reshape how creators and enterprises approach video production and editing workflows. The conversational editing interface lowers the technical barrier for complex video manipulation tasks.

  • Video generation and editing may shift from specialized software to conversational AI interfaces, affecting the competitive landscape for traditional video editing tools
  • Multimodal input handling at scale suggests progress toward more general-purpose AI systems that can reason across and generate across multiple content types
  • Integration into YouTube Shorts and Google Flow signals Google's strategy to embed generative capabilities into existing user-facing products rather than launching standalone tools

Related Video

Share
Voice & Video AIGenerative AIModel ReleasesMultimodalGoogle DeepMind

Our Briefing

Weekly signal. No noise. Built for founders, operators, and AI-curious professionals.

No spam. Unsubscribe any time.

Related stories

AI Discovers Security Flaws Faster Than Humans Can Patch Them
AI Risk & SecurityNews

AI Discovers Security Flaws Faster Than Humans Can Patch Them

Recent high-profile breaches at startups like Mercor and Vercel, combined with Anthropic's disclosure that its Mythos AI model identified thousands of previously unknown cybersecurity vulnerabilities, underscore growing demand for AI-powered security solutions. The article argues that cybersecurity vendors CrowdStrike and Palo Alto Networks, which are integrating AI into their threat detection and response capabilities, represent undervalued investment opportunities as enterprises face mounting pressure to defend against both conventional and AI-discovered attack vectors.

21 days ago· The Information
AWS Launches G7e GPU Instances for Cheaper Large Model Inference
AI HardwareTrendingModel Release

AWS Launches G7e GPU Instances for Cheaper Large Model Inference

AWS has launched G7e instances on Amazon SageMaker AI, powered by NVIDIA RTX PRO 6000 Blackwell GPUs with 96 GB of GDDR7 memory per GPU. The instances deliver up to 2.3x inference performance compared to previous-generation G6e instances and support configurations from 1 to 8 GPUs, enabling deployment of large language models up to 300B parameters on the largest 8-GPU node. This represents a significant upgrade in memory bandwidth, networking throughput, and model capacity for generative AI inference workloads.

29 days ago· AWS Machine Learning Blog
Anthropic Launches Claude Design for Non-Designers
AnthropicModel Release

Anthropic Launches Claude Design for Non-Designers

Anthropic has launched Claude Design, a new product aimed at helping non-designers like founders and product managers create visuals quickly to communicate their ideas. The tool addresses a gap for early-stage teams and individuals who need to share concepts visually but lack design expertise or resources. Claude Design integrates with Anthropic's Claude AI platform, leveraging its capabilities to streamline the visual creation process. The launch reflects growing demand for AI-powered design tools that lower barriers to entry for non-technical users.

about 1 month ago· TechCrunch AI
Google Splits TPUs Into Training and Inference Chips
AI HardwareNews

Google Splits TPUs Into Training and Inference Chips

Google is splitting its eighth-generation tensor processing units into separate chips optimized for AI training and inference, a shift the company says reflects the rise of AI agents and their distinct computational needs. The training chip delivers 2.8 times the performance of its predecessor at the same price, while the inference processor (TPU 8i) achieves 80% better performance and includes triple the SRAM of the prior generation. Both chips will launch later this year as Google continues its effort to compete with Nvidia in custom AI silicon, though the company is not directly benchmarking against Nvidia's offerings.

28 days ago· Direct