正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

I got early access to Project Genie from Google DeepMind ✨ It's unlike any realtime world model I've tried - you generate a scene from text or a photo, and then design the character who gets to explore it. I tested dozens of prompts. Here are the standout features 👇

Justine Moore

203,372 subscribers

229,613 次观看 • 5 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

I got to "play" a world model in real life. The Google DeepMind folks set up a crazy demo for Genie. You select glowing orbs to represent your scene and character. It loads the world in the model, and you navigate with joysticks like a video game 🕹️

I got to "play" a world model in real life. The Google DeepMind folks set up a crazy demo for Genie. You select glowing orbs to represent your scene and character. It loads the world in the model, and you navigate with joysticks like a video game 🕹️

Justine Moore

60,142 次观看 • 2 个月前

Vibe design is here ✨ I got early access to Stitch from Google DeepMind and was blown away - it's like partnering with a pro designer. Start with a simple prompt for a mobile or Web UI and iterate through to a clickable prototype (and code!). Watch me make "Finn's Fudge" 👇

Vibe design is here ✨ I got early access to Stitch from Google DeepMind and was blown away - it's like partnering with a pro designer. Start with a simple prompt for a mobile or Web UI and iterate through to a clickable prototype (and code!). Watch me make "Finn's Fudge" 👇

Justine Moore

80,232 次观看 • 4 个月前

Step into the map with the Street View grounding feature in Project Genie from Google DeepMind and Google Labs. Announced at I/O, this research prototype uses locations from Google Maps Street View as a foundation, letting you generate and explore interactive, 360-degree virtual environments from just a text prompt or real-world starting place. Cool, right? But… How does it actually work? 🤔 As an experimental tool, Project Genie tackles the "blank space" problem (showing both what’s in front of the camera and behind it) by utilizing Street View data to realistically generate a 360-degree view of the location you selected as the starting point for your world to generate from. Worlds generated by Genie are far more dynamic and rich because they’re created frame-by-frame based on the world description and user actions. By predicting each subsequent frame, Genie is able to simulate what it looks like to swim across an ocean, or hike to the top of a peak, marking a massive shift in interactive media and simulation pipelines. What real-world place would you want to step into and explore?

Step into the map with the Street View grounding feature in Project Genie from Google DeepMind and Google Labs. Announced at I/O, this research prototype uses locations from Google Maps Street View as a foundation, letting you generate and explore interactive, 360-degree virtual environments from just a text prompt or real-world starting place. Cool, right? But… How does it actually work? 🤔 As an experimental tool, Project Genie tackles the "blank space" problem (showing both what’s in front of the camera and behind it) by utilizing Street View data to realistically generate a 360-degree view of the location you selected as the starting point for your world to generate from. Worlds generated by Genie are far more dynamic and rich because they’re created frame-by-frame based on the world description and user actions. By predicting each subsequent frame, Genie is able to simulate what it looks like to swim across an ocean, or hike to the top of a peak, marking a massive shift in interactive media and simulation pipelines. What real-world place would you want to step into and explore?

Google AI

496,410 次观看 • 15 天前

Cool new launch for Project Genie ✨ World generation is now grounded with Google Maps. Pick a real-world location, restyle it, and draft a character to explore the scene. I turned a16z SF into a desert and wandered around as a camel.

Cool new launch for Project Genie ✨ World generation is now grounded with Google Maps. Pick a real-world location, restyle it, and draft a character to explore the scene. I turned a16z SF into a desert and wandered around as a camel.

Justine Moore

62,162 次观看 • 2 个月前

Omni from Google DeepMind just dropped 👀 It's a big step forward in video generation when it comes to character consistency, world knowledge, and editing. I've been testing it for the last few days - and I'm excited to walk through some of the key features + my clips 👇

Omni from Google DeepMind just dropped 👀 It's a big step forward in video generation when it comes to character consistency, world knowledge, and editing. I've been testing it for the last few days - and I'm excited to walk through some of the key features + my clips 👇

Justine Moore

85,139 次观看 • 2 个月前

Today we are announcing Genie 3, a general purpose world model by Google DeepMind that can generate dynamic, interactive environments with a single text prompt. World models are AI that understand facets of the world (like Veo's knowledge of intuitive physics or Genie's mastery of new environments), and serve as a key stepping stone on the path to AGI. Genie 3 is our first world model to allow interaction in real-time, while also improving consistency and realism compared to Genie 2. Learn more ➡️

Today we are announcing Genie 3, a general purpose world model by Google DeepMind that can generate dynamic, interactive environments with a single text prompt. World models are AI that understand facets of the world (like Veo's knowledge of intuitive physics or Genie's mastery of new environments), and serve as a key stepping stone on the path to AGI. Genie 3 is our first world model to allow interaction in real-time, while also improving consistency and realism compared to Genie 2. Learn more ➡️

Google AI

102,615 次观看 • 11 个月前

Here we go: Gemini 3.0 is live! Thankfully, I was able to be an early tester. It's the best model I've ever tested - nothing comes even close to it. OpenAI will have a very hard time to keep up with Google, because Gemini 3.0 will now be the benchmark for all future models. I have been invited by Google DeepMind / Google - Thanks to Google DeepMind for the #EarlyAccess Here's a summary of Gemini 3.0 with all the important benchmark evals:

Here we go: Gemini 3.0 is live! Thankfully, I was able to be an early tester. It's the best model I've ever tested - nothing comes even close to it. OpenAI will have a very hard time to keep up with Google, because Gemini 3.0 will now be the benchmark for all future models. I have been invited by Google DeepMind / Google - Thanks to Google DeepMind for the #EarlyAccess Here's a summary of Gemini 3.0 with all the important benchmark evals:

Chubby♨️

108,611 次观看 • 8 个月前

🌐 Incredibly happy to share Project Genie with the world. We announced Genie 3 in August, and since then the team worked hard to make it available to more people. Starting today, Project Genie is available to all Ultra subscribers in the US. Create an interactive world from any text prompt or image, tweak it and walk into the world you just created! Can't wait to see what you create with it 🚀🧞

🌐 Incredibly happy to share Project Genie with the world. We announced Genie 3 in August, and since then the team worked hard to make it available to more people. Starting today, Project Genie is available to all Ultra subscribers in the US. Create an interactive world from any text prompt or image, tweak it and walk into the world you just created! Can't wait to see what you create with it 🚀🧞

Shlomi Fruchter

34,622 次观看 • 5 个月前

I tried out Pomelli, the new social marketing design tool from Google Labs You just drop in your website URL, and Pomelli understands your 'Business DNA' It creates a style guide which it then uses to generate on-brand social assets. It's limited in its editing features and customization options, but I think it’s already a very helpful tool for small business owners who do not yet have the means to hire a dedicated design team.

Roberto Nickson

44,731 次观看 • 8 个月前

✨ You can design a new AI influencer from scratch based on your preferences of how they look They can look any way you want, from young to old, slim to big, short to tall. and you don't need to upload any photos cause they're synthetically generated And I made it so you get a live preview while designing it (another idea I had during my sleep last night :D) Then after you press [ Create model ], it builds up your character, generates some sample photos and then you can start taking your own photos and videos with it Or run a photo pack if you don't want to write prompts

✨ You can design a new AI influencer from scratch based on your preferences of how they look They can look any way you want, from young to old, slim to big, short to tall. and you don't need to upload any photos cause they're synthetically generated And I made it so you get a live preview while designing it (another idea I had during my sleep last night :D) Then after you press [ Create model ], it builds up your character, generates some sample photos and then you can start taking your own photos and videos with it Or run a photo pack if you don't want to write prompts

@levelsio

122,498 次观看 • 1 年前

Google Gemini Omni is here Generate, animate and edit any video with one model → Edit with your words: a character, a camera angle, the action → Motion that behaves like the real world → From reference to a cinematic scene Now on Magnific, via Magnific MCP and Spaces

Google Gemini Omni is here Generate, animate and edit any video with one model → Edit with your words: a character, a camera angle, the action → Motion that behaves like the real world → From reference to a cinematic scene Now on Magnific, via Magnific MCP and Spaces

Magnific

87,643 次观看 • 25 天前

Google DeepMind just dropped 'Genie', an AI that can generate interactive video games. This is a huge deal. Genie is trained on 200,000 hours of unsupervised public internet gaming videos and can generate video games from a single prompt or image. But here's what's insane: Despite not being trained on action or text annotations, the foundation model can determine who the main character is and enable a user to control that character in the generated world. It does this through its Latent Action Model, Video Tokenizer, and Dynamics Model (will go more in-depth on this in tomorrow's newsletter for those interested). And for those asking, yes, it's research-only and not publicly available (here come the Google memes), and it does come with some limitations, like only currently creating games at 1FPS. But this is the worst AI will ever be. Anyone will be able to create their own entirely imagined virtual worlds soon, and that's a wild sentence to say out loud.

Google DeepMind just dropped 'Genie', an AI that can generate interactive video games. This is a huge deal. Genie is trained on 200,000 hours of unsupervised public internet gaming videos and can generate video games from a single prompt or image. But here's what's insane: Despite not being trained on action or text annotations, the foundation model can determine who the main character is and enable a user to control that character in the generated world. It does this through its Latent Action Model, Video Tokenizer, and Dynamics Model (will go more in-depth on this in tomorrow's newsletter for those interested). And for those asking, yes, it's research-only and not publicly available (here come the Google memes), and it does come with some limitations, like only currently creating games at 1FPS. But this is the worst AI will ever be. Anyone will be able to create their own entirely imagined virtual worlds soon, and that's a wild sentence to say out loud.

Rowan Cheung

3,376,915 次观看 • 2 年前

I got early access to Teamily AI, and it's unlike anything I've seen before. It's not a chatbot or another productivity app. This is the world's first messenger where humans and AI agents coexist in the same conversation... Check this out 👇

I got early access to Teamily AI, and it's unlike anything I've seen before. It's not a chatbot or another productivity app. This is the world's first messenger where humans and AI agents coexist in the same conversation... Check this out 👇

Alex Colhoun

37,864 次观看 • 4 个月前

Google announces MusicLM: a model to generate music from text. Here are some crazy things it can do: 1. Given audio of a melody, it can generate new music inspired by that melody customized by prompts! Here's someone humming bella ciao turned into a cappella chorus, EDM, etc.

Google announces MusicLM: a model to generate music from text. Here are some crazy things it can do: 1. Given audio of a melody, it can generate new music inspired by that melody customized by prompts! Here's someone humming bella ciao turned into a cappella chorus, EDM, etc.

bleedingedge.ai

379,914 次观看 • 3 年前

Okay I got it from 10 seconds to 30 seconds now This is just a text script I made from ChatGPT put in textbox on Photo AI and then pressed the button and it did everything here

Okay I got it from 10 seconds to 30 seconds now This is just a text script I made from ChatGPT put in textbox on Photo AI and then pressed the button and it did everything here

@levelsio

111,147 次观看 • 11 个月前

A new real-time world model is here 👀 I tested out Dynamics Lab's Mirage 2, which was just publicly released. You can upload an image and step inside it - with game controls that guide movement + the ability to change the scene with text prompts.

A new real-time world model is here 👀 I tested out Dynamics Lab's Mirage 2, which was just publicly released. You can upload an image and step inside it - with game controls that guide movement + the ability to change the scene with text prompts.

Justine Moore

24,297 次观看 • 11 个月前

Here is my latest piece testing out what can be made with the latest update from Google DeepMind Veo 3 image to video. I take a quick look at the "Dropbear Defender" a marvel of Australian ingenuity 🚀 I've included some of prompts I used below 😁👍

Here is my latest piece testing out what can be made with the latest update from Google DeepMind Veo 3 image to video. I take a quick look at the "Dropbear Defender" a marvel of Australian ingenuity 🚀 I've included some of prompts I used below 😁👍

Captain HaHaa

85,033 次观看 • 1 年前

I built a Chrome extension that helps you extract styles from any website and generate DESIGN(.)md or SKILL(.)md files Works with Google Stitch, Claude Code, Codex etc ... and it's free!

I built a Chrome extension that helps you extract styles from any website and generate DESIGN(.)md or SKILL(.)md files Works with Google Stitch, Claude Code, Codex etc ... and it's free!

Zoltán Szőgyényi

343,351 次观看 • 3 个月前