본문으로 건너뛰기
AI NEWS JOURNAL
Google DeepMindAI NEWS / JOURNAL

Genie 4 is now available

Google introduces a new Project Genie experience for eligible Google AI Ultra subscribers, featuring Genie 4—the most realistic and interactive world model yet—enabling real-time prompt-based changes to environments, native audio adaptation, and extended session capabilities. Upgrades to Genie 3 include longer runs, 360-degree panorama grounding, and real-time in-world events. The Project Genie agent allows users to create interactive worlds through natural language prompts, while the community gallery offers curated and user-generated worlds for exploration and remixing. Safety measures like SynthID watermarking and content screening are in place, and ongoing research addresses challenges such as camera latency and scene permanence.

번역 서비스가 일시 중지되어 원문을 표시합니다.

Nov 18, 2026 Explore a new Project Genie experience for Google AI Ultra subscribers, featuring Genie 4, the Project Genie agent, and a community gallery. Diego Rivas Group Product Manager, Google DeepMind Pavan Kumar Group Product Manager, Google Labs Your browser does not support the audio element. Earlier this year we introduced Project Genie, an experimental research prototype that lets you generate and explore interactive worlds. Early testers told us they wanted deeper control over what happens inside those worlds, and easier ways to build and share them. So today, we are rolling out a new Project Genie experience to eligible Google AI Ultra subscribers, making these worlds far more responsive, creative, and social. This update unlocks first-time access to Genie 4, new upgrades to Genie 3, the Project Genie agent which helps users build their vision, and a community gallery to discover, explore, and remix worlds. Project Genie brings together our most advanced world models alongside our Gemini models, empowering you to generate, step inside, and shape worlds directly from your browser. Experience Genie 4 in Project Genie With Genie 4, our most realistic and interactive world model yet, you can now prompt mid-session to change the world you created. Just type a new prompt while you navigate your world and you can edit your environments in real time. Shift the weather, drop in a character, or redirect the action. For the first time, Genie 4 pairs these visuals with real-time native audio that adapts as the scene unfolds, from ambient soundscapes to character dialogue. Discover new Genie 3 capabilities While Genie 4 delivers our highest-fidelity visuals, physics, and native audio, Genie 3 remains available in Project Genie’s model picker when you want longer runs or panorama-seeded spaces. Today’s Genie 3 updates include: Extended sessions and world chaining: Explore for up to 3 minutes per generation (up from 60 seconds), or link multiple worlds together for longer journeys. 360-degree panorama image grounding: Seed new worlds from 360-degree panorama images. Real-time in-world events: Dynamically change the environment with natural-language prompts while you explore. Genie 3 uses real-time promptable events to connect different worlds into one continuous flight across forests, underwater ruins, and icy seas. See how 360-degree panorama grounding in Genie 3 keeps Petra’s canyon and facade consistent as you look around. Watch how Genie 3 combines longer runs, 360-degree panorama grounding, and real-time promptable events - transforming the world as you fly and even summoning a dragon to ride on command. Create new interactive experiences The new Project Genie agent takes creation beyond a single text or image prompt. Now crafting an interactive universe is as effortless as having a conversation. Simply describe your vision in natural language, and the agent orchestrates Google’s suite of multimodal models to craft initial visuals establishing your world’s signature look, paired with custom background scores tailored to the mood. You can also bring Gemini models into the session as you explore: it observes what is happening on screen, surfaces context-aware suggestion chips for where to go next, or triggers in-world events automatically as your journey unfolds. Turns a natural language prompt into an interactive spacewalk, then an alien spaceship appears on command Remix a hillside cafe into a glass pavilion in the desert. Publish custom worlds to the gallery for others to explore and remix. Explore the new gallery When you just want to jump straight into exploring, the new Project Genie gallery brings together a rich collection of curated worlds alongside creative work from the community. Transform personal photos into explorable spaces in “Living Memory,” wander through rich prehistoric habitats grounded in 360-degree panoramas in “Dino Field Guide,” or pit themed objects against one another on a desk with Gemini serving as your real-time referee in “Rock Paper Scissors.” Browse curated and community-built worlds and jump straight into exploring. “Villa Giallo,” created with Will aka BLVCKL!GHT, uses Genie 4 to turn a gothic manor into an interactive, room-by-room mystery. “The Life of Ants,” built with filmmaker Anand Gandhi, uses Genie 4’s photorealism to let you navigate a colony from an ant’s perspective. The gallery also showcases inspiring collaborations with pioneering creators who had early access to these tools. Teaming up with creative technologist Will aka BLVCKL!GHT, we created “Villa Giallo,” an atmospheric, room-by-room mystery inside a gothic manor. And with filmmaker Anand Gandhi, we built “The Life of Ants,” inviting you to navigate a complex colony from an ant’s perspective, drawing on Genie 4’s stunning photorealism. Beyond exploring curated worlds, you can also launch your vision with a simple prompt or remix existing gallery experiences alongside the Project Genie agent — tweaking the underlying world structure, soundtrack, or rules to make it uniquely your own. Once you’ve crafted something special, publish your creation to the community gallery for others to explore and remix. Learn how we are building responsibly We are committed to developing and rolling out interactive world models responsibly. All video and audio generated in Project Genie includes SynthID watermarking, and all model inputs and outputs go through safety screenings. Genie 3 and Genie 4 remain world models in the frontier research space. As the research continues to evolve, we are actively tackling key challenges such as camera latency, intricate physical interactions, real-time audio precision, and long-term scene permanence. For a deeper look into model limitations and our progress on these fronts, read our Genie 4 model research overview. Try Project Genie today Eligible Google AI Ultra subscribers can try the new Project Genie experience starting today, and Google AI Pro members can join the waitlist on the same page. Get the latest news from Google in your inbox Sign up for our newsletters with product updates, event information, special offers, and more. Done. Just one step more. Check your inbox to confirm your subscription. You can also subscribe with a different email address. Your information will be used in accordance with Google's privacy policy. You may opt out at any time.

자료 출처

원문 읽기 ↗

관련 주제

← 전체 소식 이어 읽기