正在加载视频...

视频加载失败

返回首页

GPT Image 2 launched 48 hours ago. People are already using it to make things that were impossible before. 15 insane examples you have to see: 1) Creating full 3D worlds with 1 prompt:

markgadala's profile picture

Mark Gadala-Maria

75,511 subscribers

484,164 次观看 • 2 个月前 •via X (Twitter)

新闻政治科学技术
LIVE

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

Gemini 3 has only been out for 18 hours But people are already creating insane things with it. Here are my top 13 examples, enjoy 1. 3D Pacman on tiny Planet - by TomLikesRobots
0:55

Gemini 3 has only been out for 18 hours But people are already creating insane things with it. Here are my top 13 examples, enjoy 1. 3D Pacman on tiny Planet - by TomLikesRobots

Linus ✦ Ekenstam

353,079 次观看 • 7 个月前

Tutorial: how to make equirectangular panorama with GPT Image 2 + Codex Step 1: generate an image with GPT Image 2 prompt: make equirectangular panorama of [PLACE] Step 2: feed your panorama to Codex as a reference and prompt: make mouse-controlled 3D view I'd love to see your experiments!
0:30

Tutorial: how to make equirectangular panorama with GPT Image 2 + Codex Step 1: generate an image with GPT Image 2 prompt: make equirectangular panorama of [PLACE] Step 2: feed your panorama to Codex as a reference and prompt: make mouse-controlled 3D view I'd love to see your experiments!

Kris Kashtanova

70,989 次观看 • 2 个月前

Saw some cool demos of folks using GPT-Image-2 to produce cool 3D UIs and you can actually get super realistic output with just 1 prompt = 1 image!
0:28

Saw some cool demos of folks using GPT-Image-2 to produce cool 3D UIs and you can actually get super realistic output with just 1 prompt = 1 image!

Blixt

247,222 次观看 • 2 个月前

It's only been 2 hours since Open AI launched GPT-4o, and people are going crazy over it. Here are 10 wild examples you don't want to miss: 1. Math Problems with GPT-4o
3:11

It's only been 2 hours since Open AI launched GPT-4o, and people are going crazy over it. Here are 10 wild examples you don't want to miss: 1. Math Problems with GPT-4o

Angry Tom

3,399,564 次观看 • 2 年前

GPT Image 2 is insanely good...I generated a 360° equirectangular panorama in Happycapy with just a skill + prompt. Step 1: Select the generate-image skill Step 2: Enter a prompt like: “Use a frontend 360 viewer to display an equirectangular image of […] using the GPT-Image-2 model.” Wanna see how you all get creative with this
0:45

GPT Image 2 is insanely good...I generated a 360° equirectangular panorama in Happycapy with just a skill + prompt. Step 1: Select the generate-image skill Step 2: Enter a prompt like: “Use a frontend 360 viewer to display an equirectangular image of […] using the GPT-Image-2 model.” Wanna see how you all get creative with this

Min Zhou

341,265 次观看 • 2 个月前

Gemma 4 dropped less than 48 hours ago. And people are already building wild stuff with it. 🤯 6 examples ↓
1:56

Gemma 4 dropped less than 48 hours ago. And people are already building wild stuff with it. 🤯 6 examples ↓

Vaibhav Sisinty

96,725 次观看 • 2 个月前

OpenAI's GPT-4o is now accessible to all. And people are already using it for incredible use cases. 12 wild examples: 1. Turn spreadsheets into charts
0:24

OpenAI's GPT-4o is now accessible to all. And people are already using it for incredible use cases. 12 wild examples: 1. Turn spreadsheets into charts

Madni Aghadi

1,621,925 次观看 • 2 年前

ChatGPT's new image generator is insane. People are creating things you wouldn’t believe. Here are 6 ways you can use it today: 1. Outfit-on-Model Generation
1:49

ChatGPT's new image generator is insane. People are creating things you wouldn’t believe. Here are 6 ways you can use it today: 1. Outfit-on-Model Generation

God of Prompt

39,376 次观看 • 1 年前

#ICCV2025 🤩3D world generation is cool, but it is cooler to play with the worlds using 3D actions 👆💨, and see what happens! — Introducing *WonderPlay*: Now you can create dynamic 3D scenes that respond to your 3D actions from a single image! Web: 🧵1/7
0:46

#ICCV2025 🤩3D world generation is cool, but it is cooler to play with the worlds using 3D actions 👆💨, and see what happens! — Introducing *WonderPlay*: Now you can create dynamic 3D scenes that respond to your 3D actions from a single image! Web: 🧵1/7

Hong-Xing (Koven) Yu

57,590 次观看 • 1 年前

"That's impossible for AI to create" Until OpenAI launched 4o image generation a day ago. The 16 mind-blowing examples (100% AI-made): 1. Ghibli style images
1:37

"That's impossible for AI to create" Until OpenAI launched 4o image generation a day ago. The 16 mind-blowing examples (100% AI-made): 1. Ghibli style images

Madni Aghadi

191,111 次观看 • 1 年前

Codex + GPT-Image-2 + Three.js = instant interactive 3D worlds 🌍
0:22

Codex + GPT-Image-2 + Three.js = instant interactive 3D worlds 🌍

Givros

40,225 次观看 • 2 个月前

Less than 24 hours since Hailuo dropped 02 and people are already creating some wild stuff. Real Veo 3 competitor? 13 insane examples 🧵👇 1. Action scenes and VFX compilation
1:01

Less than 24 hours since Hailuo dropped 02 and people are already creating some wild stuff. Real Veo 3 competitor? 13 insane examples 🧵👇 1. Action scenes and VFX compilation

TechHalla

103,590 次观看 • 1 年前

this workflow save you tons of time for creating longer films the image include everything in the scene, so you dont need to @ things multiple time in the prompts to keep consistent on with shot list image, you can generate multiple shot using 1 prompt
0:25

this workflow save you tons of time for creating longer films the image include everything in the scene, so you dont need to @ things multiple time in the prompts to keep consistent on with shot list image, you can generate multiple shot using 1 prompt

el.cine

15,014 次观看 • 1 个月前

🚨GROK 4 DROPS—INSANE DEMOS HAVE THE INTERNET BUZZING Less than 24 hours since xAI launched Grok 4, and the internet is already buzzing. People are diving deep into wild use cases and pushing it to the max. Here are three jaw-dropping examples you need to see, starting with mind-blowing physics tests and creative benchmarks. The world hasn't seen anything like this before. Source: Dan
0:07

🚨GROK 4 DROPS—INSANE DEMOS HAVE THE INTERNET BUZZING Less than 24 hours since xAI launched Grok 4, and the internet is already buzzing. People are diving deep into wild use cases and pushing it to the max. Here are three jaw-dropping examples you need to see, starting with mind-blowing physics tests and creative benchmarks. The world hasn't seen anything like this before. Source: Dan

Mario Nawfal

190,035 次观看 • 11 个月前

2 weeks ago, we publicly released Pancake to the world. since then, two things have changed for me: 1. I realized that people are incredibly creative and are using Pancake in ways I hadn’t even thought of. 2. I had to mute my Stripe notifications. several examples of usage in thread
0:50

2 weeks ago, we publicly released Pancake to the world. since then, two things have changed for me: 1. I realized that people are incredibly creative and are using Pancake in ways I hadn’t even thought of. 2. I had to mute my Stripe notifications. several examples of usage in thread

Will Marquis

142,938 次观看 • 21 天前

This is peak... Google just unveiled Genie 3 This AI generates photorealistic & 3D worlds from a text prompt and image... that you can explore in real-time Clearing a path towards AGI 10 wild examples + how to try below 1. Control a shiny marble
0:20

This is peak... Google just unveiled Genie 3 This AI generates photorealistic & 3D worlds from a text prompt and image... that you can explore in real-time Clearing a path towards AGI 10 wild examples + how to try below 1. Control a shiny marble

Linus ✦ Ekenstam

44,603 次观看 • 5 个月前

This seems impossible: A Twitter account made a post with the shooter’s name almost 2 1/2 years ago, and the header of that account has an image from a website called “Time Machine”. To make things even crazier, the Trump Butler photograph superimposed over that image shows that it’s almost a perfect outline of that image. Watch.
0:30

This seems impossible: A Twitter account made a post with the shooter’s name almost 2 1/2 years ago, and the header of that account has an image from a website called “Time Machine”. To make things even crazier, the Trump Butler photograph superimposed over that image shows that it’s almost a perfect outline of that image. Watch.

Brian Krassenstein

1,542,618 次观看 • 2 个月前

GPT-Image-2 was just released... It's the best image model (By a wide margin) Heres how to use GPT-Image-2 in ChatGPT, OpenAI Playground and of Course - Codex. TIMESTAMPS 00:00 Intro 01:27 Initial Tests of GPT-Image-2 02:24 It can GENERATE working BARCODES? 03:40 11 Edits one Prompt 06:40 Creating Cartoons 07:40 Overlay Explanations 08:50 How to Get Started 10:51 IPhone Mockup Images (Amazing) 15:43 Using GPT-Image in OpenAI Playground 16:11 Generate images in 4k 17:44 The FIRST limitation... Its bad at counting 18:26 Using GPT-Image in Codex (Agentic Image Gen)
22:26

GPT-Image-2 was just released... It's the best image model (By a wide margin) Heres how to use GPT-Image-2 in ChatGPT, OpenAI Playground and of Course - Codex. TIMESTAMPS 00:00 Intro 01:27 Initial Tests of GPT-Image-2 02:24 It can GENERATE working BARCODES? 03:40 11 Edits one Prompt 06:40 Creating Cartoons 07:40 Overlay Explanations 08:50 How to Get Started 10:51 IPhone Mockup Images (Amazing) 15:43 Using GPT-Image in OpenAI Playground 16:11 Generate images in 4k 17:44 The FIRST limitation... Its bad at counting 18:26 Using GPT-Image in Codex (Agentic Image Gen)

Riley Brown

35,552 次观看 • 2 个月前

Ok GPT-5.5 is insane. People can't stop building. 10 wild examples: 1. Seinfeld Apartment beat 'em up game through Codex including 3D assets
0:29

Ok GPT-5.5 is insane. People can't stop building. 10 wild examples: 1. Seinfeld Apartment beat 'em up game through Codex including 3D assets

Min Choi

274,046 次观看 • 2 个月前

With ChatGPT Images 2.0 we can now create an image from prompt, then with GPT 5.4 Pro convert it to a CAD model using ForgeCAD. > Prompt: Make a detailed wood gong fu tea tray.
0:45

With ChatGPT Images 2.0 we can now create an image from prompt, then with GPT 5.4 Pro convert it to a CAD model using ForgeCAD. > Prompt: Make a detailed wood gong fu tea tray.

Ruben Kostandyan

747,473 次观看 • 2 个月前