惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Cisco Talos Blog
Cisco Talos Blog
The Hacker News
The Hacker News
L
LINUX DO - 最新话题
P
Privacy & Cybersecurity Law Blog
C
Cyber Attacks, Cyber Crime and Cyber Security
S
Secure Thoughts
S
Schneier on Security
MyScale Blog
MyScale Blog
月光博客
月光博客
U
Unit 42
www.infosecurity-magazine.com
www.infosecurity-magazine.com
AI
AI
N
News and Events Feed by Topic
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
爱范儿
爱范儿
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
S
Securelist
B
Blog RSS Feed
Spread Privacy
Spread Privacy
H
Help Net Security
Know Your Adversary
Know Your Adversary
I
Intezer
Hacker News - Newest:
Hacker News - Newest: "LLM"
V
V2EX
MongoDB | Blog
MongoDB | Blog
GbyAI
GbyAI
博客园 - 叶小钗
D
DataBreaches.Net
T
Troy Hunt's Blog
Project Zero
Project Zero
Last Week in AI
Last Week in AI
Y
Y Combinator Blog
P
Privacy International News Feed
The Last Watchdog
The Last Watchdog
K
Kaspersky official blog
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
Latest news
Latest news
S
Security @ Cisco Blogs
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
V2EX - 技术
V2EX - 技术
Hacker News: Ask HN
Hacker News: Ask HN
The GitHub Blog
The GitHub Blog
C
Cisco Blogs
C
CERT Recently Published Vulnerability Notes
Attack and Defense Labs
Attack and Defense Labs
T
Threatpost
O
OpenAI News
Recorded Future
Recorded Future
Help Net Security
Help Net Security
罗磊的独立博客

Google DeepMind

Reconstructing Pelé’s “lost” goal We're rolling out AlphaEvolve widely to solve Google Cloud customers' hardest problems. The latest AI news we announced in June 2026 Google DeepMind and A24 announce first-of-its-kind research partnership New research shows how AMIE, our medical AI, could help manage health conditions. The latest AI news we announced in May 2026 9 demos of Gemini Omni and Gemini 3.5 in action Running Guide agent: A step towards running unbounded Making it easier to understand how content was created and edited Simulate real-world places with Project Genie and Street View Gemini for Science: AI experiments and tools for a new era of discovery We’re launching the Google DeepMind Accelerator program in Asia Pacific to tackle environmental risks. Find out how AlphaEvolve has gone from research to solving real-life problems. Join the new AI Agents Vibe Coding Course from Google and Kaggle Gemini Robotics ER-1.6 enhances reasoning to help robots navigate real-world tasks. The latest AI news we announced in March 2026 Measuring progress toward AGI: A cognitive framework Broadening advanced AI education across Africa Platform 37 and The AI Exchange: new spaces for AI innovation and discovery The latest AI news we announced in February Ask a Techspert: What’s a world model? Gemini 3 Deep Think: Advancing science, research and engineering The latest AI news we announced in January Advancing AI benchmarking with Game Arena Project Genie: Experimenting with infinite, interactive worlds
Create new worlds in Project Genie with these 4 tips
Molly McHugh-Johnson · 2026-03-04 · via Google DeepMind

Here’s how to write great prompts for Project Genie, which lets you create and explore your own interactive worlds.

General summary

Project Genie lets you create interactive worlds using text and images. If you are a Google AI Ultra Subscriber in the U.S. over 18 you can use it. Start world-building with detailed environment descriptions, unique characters and action-oriented prompts.

Summaries were generated by Google AI. Generative AI is experimental.

Bullet points

  • "Create new worlds in Project Genie with these 4 tips" shows you how to build interactive worlds.
  • Describe your environment with details like weather, objects, and the overall feel you want.
  • Pick a character and how it moves to navigate your world; it can be anything you want!
  • Upload images to create worlds, centering your character with enough background to define it.
  • Use short, direct prompts and switch between first and third-person views to explore.

Summaries were generated by Google AI. Generative AI is experimental.

Basic explainer

Project Genie lets you build and walk around in your own cool worlds using AI. You can type in what you want the world to look like, like a forest or the moon, and even add your own pictures. Then, you pick a character to explore it all, like a giraffe or a robot. To make it work best, use short, clear instructions when you're telling the AI what to do.

Summaries were generated by Google AI. Generative AI is experimental.

Explore other styles:

A screen capture of Project Genie, an experimental interface showing a grid of circular images, many of which appear to be 360-degree views, with a large, central black globe labeled Create your own

Your browser does not support the audio element.

Listen to article

This content is generated by Google AI. Generative AI is experimental

[[duration]] minutes

We recently introduced Project Genie, an experimental research prototype that lets you create, explore and remix your own interactive worlds. With Project Genie, you can develop worlds with characters and environments, then navigate them in real time, like by journeying to a new, imaginary planet or diving underwater with sea creatures. Project Genie is currently available to Google AI Ultra Subscribers in the U.S. over 18, with plans to expand further.

You can prompt Project Genie with just text, or with text and images. If you’re ready to bring your imaginary world to life, here are some tips on how to prompt Project Genie as well as features to try.

1. Describe the environment in detail

Start by writing out what kind of environment you want — for example, you could choose a forest, a city, the moon…you get the idea. Be specific with the details: Is the forest lush or wintry? The city could be bustling or empty. Maybe the moon is made of cheese! Also add any structures or objects you want, and weather details, like wind or snow. And think about what you want the world to feel like; sure, it could be photo-realistic and look like what you see around you, or it could look like a cartoon or video game.

2. Choose a character

Your character is what allows you to navigate the world, and it can be anything, from a tiny blue giraffe to a giant pixelated doll. You can add details like how it moves (maybe it flies, rolls on wheels or runs backwards) and what kind of effect it has — maybe every time it hops forward, a puff of smoke follows behind it.

3. Make worlds from your own images

Instead of starting with just text to create an environment, you also have the option to start with your own images. Upload your image and add any other environment-defining details (like whether you want things to look dark and stormy or like they’re made of a slimy substance). Be sure to use an image where your character is centered in the frame and there's enough background visible to define the environment.

4. Use direct, action-oriented language and set the mood with sensory details

Short, declarative statements work best when you’re prompting Project Genie. For example, the text prompt could be “an underwater scene with lots of coral,” and your character could be a goldfish. Need help crafting these kinds of prompts? You can always use the Gemini app for assistance in rewriting or adjusting them. Project Genie will also show you a preview of your world and character using Nano Banana Pro so you can see what they’ll look like and how navigation will appear. If you want to adjust, you can modify your prompt and fine-tune things in real time before you start actually exploring.

5. Try switching between first and third-person perspectives

Once you’ve created an environment and a character, you can decide how to explore it all. You can navigate through the eyes of the character (the first-person view) or by watching the character from above (third-person view). Just select the perspective button to choose which viewpoint you want as you take a tour through your world.

World_SocialShare

Get more stories from Google in your inbox.

Done. Just one step more.

Check your inbox to confirm your subscription.

You are already subscribed to our newsletter.

You can also subscribe with a

Related stories