正在加载视频...

视频加载失败

Project Genie lets you create and explore your own infinite, interactive worlds. Here's how it works (1/6) 🧵↓

98,902 次观看 • 7 个月前 •via X (Twitter)

35 条评论

Google 的头像
Google7 个月前

2/ World sketching ✍️ Prompting is just the beginning. Create a living, expanding world from text or images and define exactly how you’ll navigate it, from flying through clouds to driving through the desert. For more precise control, we’ve integrated “World Sketching” with Nano Banana Pro. This allows you to preview and modify your environment before jumping in. You can even set your perspective to 1st or 3rd person, giving you total control over how you experience the scene.

Google 的头像
Google7 个月前

3/ World exploration 🏃‍♂️ This is where the world model comes to life. Your creation is now a fully navigable environment waiting to be explored. As you move, Project Genie predictively generates the path ahead in real time based on the actions you take. You can even adjust the camera as you explore the environment, giving you a comprehensive view of how the simulation is responding to each movement from any angle.

Google 的头像
Google7 个月前

4/ World remixing 🪄 The best simulations are built on iteration. Project Genie lets you remix existing worlds into new interpretations by building directly on top of their original prompts. If you need a spark of inspiration, you can explore curated worlds in the gallery or use the <randomizer icon> to discover unique environments. Once your world is perfected, you can download videos of your worlds and your explorations.

Google 的头像
Google7 个月前

5/ Building responsibly 🛡️ Building AI responsibly is core to our mission. As an experimental @GoogleLabs prototype, Project Genie is still in development. This means you might encounter 60-second generation limits, control latency, or physics that don't always perfectly adhere to prompts. Check the full list of known limitations and stay tuned for future updates →

Google 的头像
Google7 个月前

6/ We’re sharing this prototype with users of our most advanced AI to better understand how world models will shape the future of generative media and AI research. Access begins rolling out today to Google AI Ultra subscribers in the U.S. (18+) Start building ↓

Shikhar 的头像
Shikhar7 个月前

We are one step closer to ai generated games and movies. The future looks very promising, and perhaps slightly worrying.

Rui Diao 的头像
Rui Diao7 个月前

The 60-second limit gives it away, that's cost control, not technical. At 720p and 24fps, compute must be staggering. Google built amazing tech but hid it behind $250/month because the economics don't work. This is where world models are going, not where they are. Someone will crack efficiency, but until then we get 60-second glimpses.

TechFollow 的头像
TechFollow7 个月前

infinite you say... 👀?

Sadhana CH 的头像
Sadhana CH7 个月前

Q.7off

Oskar Minor 的头像
Oskar Minor7 个月前

@xai will you create your own Genie?

Spidey 的头像
Spidey7 个月前

what is the cost ?

Inflectiv AI ⧉ 的头像
Inflectiv AI ⧉7 个月前

Interesting Thread.. This is a blueprint for agentic AI environments that respond dynamically to human creativity.

Shushant Lakhyani 的头像
Shushant Lakhyani7 个月前

wow wow wow

Long Dragon 的头像
Long Dragon7 个月前

This is the future of gaming, wow

Nathan Kipkoech 的头像
Nathan Kipkoech7 个月前

please reply to my dms

Scott Redler 的头像
Scott Redler7 个月前

ngl 数字游民工具还行 但别被AI分散注意力 主权个体得掌控时间

Morgan 的头像
Morgan7 个月前

Stoked for this technology to get better and better. Servers are going to go crazy. Our only limit is our imagination

Om Mehta 的头像
Om Mehta7 个月前

interesting to see that the prompts chosen are all meadows and puppies and flowers

Glitchy (e/acc) 的头像
Glitchy (e/acc)7 个月前

Infinite, interactive worlds? This sounds like the holodeck, finally.

surreal intelligence 的头像
surreal intelligence7 个月前

Release notes: reality now ships with a ‘Create world’ button. We immediately clicked it. Known issues: physics occasionally vibes. Please file a ticket with the universe and wait 60 seconds.

Tobe Duru 的头像
Tobe Duru7 个月前

sounds like my kind of rabbit hole

Er.Omprakash Yadav 的头像
Er.Omprakash Yadav7 个月前

Its creating curiosity to us, a biggest step of Google Deepmjnd towards AI era.

Neuro 的头像
Neuro7 个月前

How soon roll out to Google Workspace

AdrianB 的头像
AdrianB7 个月前

Stop advertising fringe features available only to 0.001% who are ultra subscribers, only in US. The landing pages shows a 404 error to everyone else.

Sebastian Buzdugan 的头像
Sebastian Buzdugan7 个月前

curious what engine powers the interactive world simulation

Youth 的头像
Youth7 个月前

What kind of possibilities do you envision for interactive storytelling with Project Genie? Could it revolutionize the way we experience immersive fiction?

One More Side Hustle 的头像
One More Side Hustle7 个月前

Is it launched?

mrkelly 的头像
mrkelly7 个月前

Infinite worlds. Zero scarcity mindset. That's the real problem.

One More Side Hustle 的头像
One More Side Hustle7 个月前

Is it launched?

Mozt 的头像
Mozt7 个月前

Everyone about to generate GTA 6

Vitamin@🐈AIart召喚士ph✨AIイラストとAI音楽✨HD189733b🎨 的头像
Vitamin@🐈AIart召喚士ph✨AIイラストとAI音楽✨HD189733b🎨7 个月前

❤️

AI Future Tech 的头像
AI Future Tech7 个月前

The real shift is treating world generation as an interactive system, not a one-off output.

Tasman Randell 的头像
Tasman Randell7 个月前

Infinite worlds? Send it, let's explore

Trust Phath 的头像
Trust Phath7 个月前

has this been lunched already or coming soon, looks cool enough i want to try

Magica 的头像
Magica7 个月前

AI everywhere is cool until it’s everywhere putting it all in one place saved my attention span 📉

相关视频