正在加载视频...

视频加载失败

返回首页

Gemini 2.5 Flash just got a few new updates: You'll see enhanced step-by-step help for homework, better-organized responses, and improvements in image understanding. Here’s a breakdown of what’s new 🧵

GeminiApp's profile picture

Google Gemini

594,454 subscribers

321,868 次观看 • 1 年前 •via X (Twitter)

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

Image generation with Gemini just got a bananas upgrade and is the new state-of-the-art image generation and editing model. 🤯 From photorealistic masterpieces to mind-bending fantasy worlds, you can now natively produce, edit and refine visuals with new levels of reasoning, control and creativity. A quick dive into Gemini 2.5 Flash’s capabilities 🧵
0:18

Image generation with Gemini just got a bananas upgrade and is the new state-of-the-art image generation and editing model. 🤯 From photorealistic masterpieces to mind-bending fantasy worlds, you can now natively produce, edit and refine visuals with new levels of reasoning, control and creativity. A quick dive into Gemini 2.5 Flash’s capabilities 🧵

Google DeepMind

1,485,278 次观看 • 1 年前

1/ Gemini 2.5 is here, and it’s our most intelligent AI model ever. Our first 2.5 model, Gemini 2.5 Pro Experimental is a state-of-the-art thinking model, leading in a wide range of benchmarks – with impressive improvements in enhanced reasoning and coding and now #1 on Arena by a significant margin. With a model this intelligent, we wanted to get it to people as quickly as possible. Find it on Google AI Studio and in the Google Gemini for Gemini Advanced users now – and in Vertex in the coming weeks. This is the start of a new era of thinking models – and we can’t wait to see where things go from here.
0:14

1/ Gemini 2.5 is here, and it’s our most intelligent AI model ever. Our first 2.5 model, Gemini 2.5 Pro Experimental is a state-of-the-art thinking model, leading in a wide range of benchmarks – with impressive improvements in enhanced reasoning and coding and now #1 on Arena by a significant margin. With a model this intelligent, we wanted to get it to people as quickly as possible. Find it on Google AI Studio and in the Google Gemini for Gemini Advanced users now – and in Vertex in the coming weeks. This is the start of a new era of thinking models – and we can’t wait to see where things go from here.

Sundar Pichai

865,049 次观看 • 1 年前

Just gave Tripo Studio a spin and is wild! You can turn any image into a 3D model with AI and then tweak it endlessly with different colors, textures... Here’s a step-by-step guide to show you how (prompts included) 🧵👇
0:10

Just gave Tripo Studio a spin and is wild! You can turn any image into a 3D model with AI and then tweak it endlessly with different colors, textures... Here’s a step-by-step guide to show you how (prompts included) 🧵👇

TechHalla

46,859 次观看 • 1 年前

Mastering: a step-by-step breakdown of my process
0:13

Mastering: a step-by-step breakdown of my process

Eduard

59,227 次观看 • 3 年前

Drophunting just got an upgrade! 🪂 New features just dropped on CryptoRank Drophunting to help you track airdrops smarter. Filter tasks, track progress, and never miss a drop. 🔗 Here’s what’s new & how to use it to your advantage 🧵
0:17

Drophunting just got an upgrade! 🪂 New features just dropped on CryptoRank Drophunting to help you track airdrops smarter. Filter tasks, track progress, and never miss a drop. 🔗 Here’s what’s new & how to use it to your advantage 🧵

CryptoRank.io

116,882 次观看 • 1 年前

'AI is useless..' they say but AI can generate $100k ad for a few bucks in 2 hours this new Higgsfield SHOTS can turn one image into 9 cinematic shots, keep actor and product consistent.. no need prompts at all step by step tutorial:
0:17

'AI is useless..' they say but AI can generate $100k ad for a few bucks in 2 hours this new Higgsfield SHOTS can turn one image into 9 cinematic shots, keep actor and product consistent.. no need prompts at all step by step tutorial:

el.cine

141,547 次观看 • 10 个月前

GPT Image 2.5 + Gemini Omni Flash
0:10

Sensitive content

GPT Image 2.5 + Gemini Omni Flash

えむとさサン

70,171 次观看 • 1 个月前

🧵 breakdown thread of the Halo energy shield vfx! (there's a couple approaches you could take for this, and a lot of optimisations possible for each part, so take this more as a general 'approach' than a specific step-by-step!) 1/5
0:19

🧵 breakdown thread of the Halo energy shield vfx! (there's a couple approaches you could take for this, and a lot of optimisations possible for each part, so take this more as a general 'approach' than a specific step-by-step!) 1/5

SkULLY 💀🎃

11,150 次观看 • 1 年前

Pixel has always used AI to improve your photos. And now, thanks to the help of Gemini models, it can help you become a better photographer. Camera Coach analyzes a single frame of your scene, and gives you step-by-step instructions on taking a great photo¹ 📷 #MadeByGoogle
0:12

Pixel has always used AI to improve your photos. And now, thanks to the help of Gemini models, it can help you become a better photographer. Camera Coach analyzes a single frame of your scene, and gives you step-by-step instructions on taking a great photo¹ 📷 #MadeByGoogle

Made by Google

35,048 次观看 • 1 年前

The new is live. Built for the next generation of music creators. Here’s what’s new 🧵
0:16

The new is live. Built for the next generation of music creators. Here’s what’s new 🧵

Opulous

87,407 次观看 • 1 年前

This is wild 🤯 Arcads just dropped Emotion Control and people are going crazy over it. AI actors can now laugh, whisper, or scream just by typing tags into a script. Here’s Step-by-step guide 🧵
0:18

This is wild 🤯 Arcads just dropped Emotion Control and people are going crazy over it. AI actors can now laugh, whisper, or scream just by typing tags into a script. Here’s Step-by-step guide 🧵

Abhishek

80,197 次观看 • 1 年前

How to create an "Aging Effect" video using Midjourney v5 & RunwayML 🧵 Thread w/ step-by-step breakdown of workflow
0:14

How to create an "Aging Effect" video using Midjourney v5 & RunwayML 🧵 Thread w/ step-by-step breakdown of workflow

Nick St. Pierre

1,813,990 次观看 • 3 年前

Design ANY room for FREE 💥 Drawing from scratch lets you put your ideas right on the canvas. And it’s now available on Maket for FREE! Here’s a step by step breakdown 👇
0:14

Design ANY room for FREE 💥 Drawing from scratch lets you put your ideas right on the canvas. And it’s now available on Maket for FREE! Here’s a step by step breakdown 👇

Maket

290,137 次观看 • 6 个月前

Since launching Veo 2, we’ve built new capabilities and addressed a few pain points to help filmmakers and creatives. 📽️✨ Here’s a quick rundown. 🧵
0:12

Since launching Veo 2, we’ve built new capabilities and addressed a few pain points to help filmmakers and creatives. 📽️✨ Here’s a quick rundown. 🧵

Google DeepMind

170,187 次观看 • 1 年前

Stay one step ahead. Meet the all-new #Googlebook powered by #SnapdragonXSeries. Designed for google Gemini Intelligence, it combines premium performance, proactive help, and seamless Android experiences to keep you in your flow.
0:12

Stay one step ahead. Meet the all-new #Googlebook powered by #SnapdragonXSeries. Designed for google Gemini Intelligence, it combines premium performance, proactive help, and seamless Android experiences to keep you in your flow.

Snapdragon

33,838 次观看 • 1 个月前

Snaps just got a new feel. Check out the improved UX for smoother navigation across all campaigns: → A guided step-by-step walkthrough → Improved navigation and aesthetics → Optimized mobile version for snapping on the go Who will be snapping more now?
0:11

Snaps just got a new feel. Check out the improved UX for smoother navigation across all campaigns: → A guided step-by-step walkthrough → Improved navigation and aesthetics → Optimized mobile version for snapping on the go Who will be snapping more now?

Cookie DAO 🍪

24,087 次观看 • 1 年前