Загрузка видео...

Не удалось загрузить видео

На главную

Excited to share Muse Spark! It's a strong natively multimodal model with many surprising properties that emerged. Here, the model is able to use Python tools to make a playable Sudoku game on the web from an image input of the board. ✨

mattdeitke's profile picture

Matt Deitke

13,867 subscribers

29,581 просмотров • 4 месяцев назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

With Gemini 3, you can take an image of anything, like a board game, a floor plan, or a doodle, and make it an interactive experience. This is because of Gemini 3’s deep multimodal understanding. The model is able to analyze the content of the image, distill the most compelling parts, and then translate the image’s details into a functional, interactive experience.
0:47

With Gemini 3, you can take an image of anything, like a board game, a floor plan, or a doodle, and make it an interactive experience. This is because of Gemini 3’s deep multimodal understanding. The model is able to analyze the content of the image, distill the most compelling parts, and then translate the image’s details into a functional, interactive experience.

Google AI

98,340 просмотров • 9 месяцев назад

1/ Excited to launch an experiment today - introducing Window, a way to use your own AI models on the web - including local ones! It's a bet on a new kind of AI app emerging, one that shifts model authentication and management to the user.
0:52

1/ Excited to launch an experiment today - introducing Window, a way to use your own AI models on the web - including local ones! It's a bet on a new kind of AI app emerging, one that shifts model authentication and management to the user.

Alex Atallah

390,051 просмотров • 3 лет назад

From LA to New York, the model continuously impresses me. This time utilizing an Image To World, the consistency in aesthetics from the input image is remarkable.
0:57

From LA to New York, the model continuously impresses me. This time utilizing an Image To World, the consistency in aesthetics from the input image is remarkable.

Theoretically Media

34,467 просмотров • 7 месяцев назад

The model that is better than Opus. Muse Spark is now available for agentic trading on Beep. Be the first to trade with Spark AI Agent:
1:03

The model that is better than Opus. Muse Spark is now available for agentic trading on Beep. Be the first to trade with Spark AI Agent:

Beep

145,803 просмотров • 1 месяц назад

We’re excited to announce 𝗚𝗲𝗺𝗶𝗻𝗶: Google’s largest and most capable AI model. Built to be natively multimodal, it can understand and operate across text, code, audio, image and video - and achieves state-of-the-art performance across many tasks. 🧵
1:30

We’re excited to announce 𝗚𝗲𝗺𝗶𝗻𝗶: Google’s largest and most capable AI model. Built to be natively multimodal, it can understand and operate across text, code, audio, image and video - and achieves state-of-the-art performance across many tasks. 🧵

Google DeepMind

1,316,388 просмотров • 2 лет назад

Meta opened the weights this morning. It's already living on a Mac. Muse Glimmer 30B, running locally in Osaurus. It analyzed an image and built a playable game. Your hardware. Your model. No subscription.
0:40

Meta opened the weights this morning. It's already living on a Mac. Muse Glimmer 30B, running locally in Osaurus. It analyzed an image and built a playable game. Your hardware. Your model. No subscription.

Osaurus

23,349 просмотров • 24 дней назад

💛 new version of Sketch is out! 〜 we worked on an update to the web app inspector to include all the new properties from frames, stacks and graphics. now it's easy to copy values, css, and a box model preview 〜 please, play around with it! (˶ᵔ ᵕ ᵔ˶)✨
0:25

💛 new version of Sketch is out! 〜 we worked on an update to the web app inspector to include all the new properties from frames, stacks and graphics. now it's easy to copy values, css, and a box model preview 〜 please, play around with it! (˶ᵔ ᵕ ᵔ˶)✨

rc

11,577 просмотров • 1 год назад

Muse Spark 1.2 supports a broad range of multimodal tasks, from turning visuals into working code to translating perception into physical action. It also brings robust audio-visual understanding to enable video-heavy workflows common in real-world enterprise use. Today, we’re sharing new evals and demos that illustrate the breadth of the model’s visual understanding and reasoning capabilities. Let’s start with a demo that shows how Muse Spark parses multimodal observations and calls tools to guide a robot to navigate in an unstructured environment to find a rubber duck. 🧵👇
0:43

Muse Spark 1.2 supports a broad range of multimodal tasks, from turning visuals into working code to translating perception into physical action. It also brings robust audio-visual understanding to enable video-heavy workflows common in real-world enterprise use. Today, we’re sharing new evals and demos that illustrate the breadth of the model’s visual understanding and reasoning capabilities. Let’s start with a demo that shows how Muse Spark parses multimodal observations and calls tools to guide a robot to navigate in an unstructured environment to find a rubber duck. 🧵👇

AI at Meta

52,415 просмотров • 15 дней назад

Excited to share an early preview of our gemini 2.0 flash thinking model with all it's raw thoughts visible. Here's the model trying to solve a Putnam 2024 with multiple approaches, and then self-verifies that it's answer was correct.
0:41

Excited to share an early preview of our gemini 2.0 flash thinking model with all it's raw thoughts visible. Here's the model trying to solve a Putnam 2024 with multiple approaches, and then self-verifies that it's answer was correct.

Ankesh Anand

80,417 просмотров • 1 год назад

Muse Image from @aiatmeta is live on fal. It's an agentic image model that plans your composition, uses tools, and self-corrects before you ever see a result. Complex briefs hold together instead of falling apart.
0:28

Muse Image from @aiatmeta is live on fal. It's an agentic image model that plans your composition, uses tools, and self-corrects before you ever see a result. Complex briefs hold together instead of falling apart.

fal

34,229 просмотров • 8 дней назад

How can agents understand the world from diverse language? 🌎 Excited to introduce Dynalang, an agent that learns to understand language by 𝙢𝙖𝙠𝙞𝙣𝙜 𝙥𝙧𝙚𝙙𝙞𝙘𝙩𝙞𝙤𝙣𝙨 𝙖𝙗𝙤𝙪𝙩 𝙩𝙝𝙚 𝙛𝙪𝙩𝙪𝙧𝙚 with a multimodal world model!
0:20

How can agents understand the world from diverse language? 🌎 Excited to introduce Dynalang, an agent that learns to understand language by 𝙢𝙖𝙠𝙞𝙣𝙜 𝙥𝙧𝙚𝙙𝙞𝙘𝙩𝙞𝙤𝙣𝙨 𝙖𝙗𝙤𝙪𝙩 𝙩𝙝𝙚 𝙛𝙪𝙩𝙪𝙧𝙚 with a multimodal world model!

Jessy Lin

107,579 просмотров • 3 лет назад

It's wild what you can one-shot with Gemini 3 and Nano Banana Pro in AIS. Here's an app to relight an image: > Use a 3D environment with a bust of a person and a light source, I should be able to move the light source around to cast shadows in different ways, add multiple light sources, etc. Then I should be able to capture the scene, pass it alongside an input image to Nano Banana Pro to change the lighting on an input
0:43

It's wild what you can one-shot with Gemini 3 and Nano Banana Pro in AIS. Here's an app to relight an image: > Use a 3D environment with a bust of a person and a light source, I should be able to move the light source around to cast shadows in different ways, add multiple light sources, etc. Then I should be able to capture the scene, pass it alongside an input image to Nano Banana Pro to change the lighting on an input

fofr

25,907 просмотров • 9 месяцев назад

Today, we're launching Muse, an AI model specifically trained for fiction. We've been testing Muse with hundreds of authors for months, and we're excited to finally share it with the world.
1:24

Today, we're launching Muse, an AI model specifically trained for fiction. We've been testing Muse with hundreds of authors for months, and we're excited to finally share it with the world.

james yu

1,406,419 просмотров • 1 год назад

We're super excited to introduce Zeno-1, our advanced image generation model, with a bunch of control tools, all available on Shakker AI!
1:23

We're super excited to introduce Zeno-1, our advanced image generation model, with a bunch of control tools, all available on Shakker AI!

ShakkerAI

27,296 просмотров • 1 год назад

Idefics3-Llama is out! 💥 It's a multimodal model based on Llama 3.1 that accepts arbitrary number of interleaved images with text with a huge context window (10k tokens!) 😍 Link to demo and model in the next one 😏
0:37

Idefics3-Llama is out! 💥 It's a multimodal model based on Llama 3.1 that accepts arbitrary number of interleaved images with text with a huge context window (10k tokens!) 😍 Link to demo and model in the next one 😏

merve

28,017 просмотров • 2 лет назад

A tool returns an image of a secret number. The model reads it back. 👁️ TanStack AI now supports multimodal tool results: return an Array<ContentPart> with an image part and the model sees the actual pixels - not a stringified blob.
0:40

A tool returns an image of a secret number. The model reads it back. 👁️ TanStack AI now supports multimodal tool results: return an Array<ContentPart> with an image part and the model sees the actual pixels - not a stringified blob.

TANSTACK

16,098 просмотров • 3 месяцев назад

Is Meta still chasing a frontier model? Well, yes, Muse Spark was but an appetizer, according to Alexandr Wang. Full pod here -
3:49

Is Meta still chasing a frontier model? Well, yes, Muse Spark was but an appetizer, according to Alexandr Wang. Full pod here -

Ashlee Vance

18,297 просмотров • 3 месяцев назад

Excited to share a glimpse of my first app with SwiftUI 😌. I've built from scratch a user-friendly ios app, empowering users to explore and examine the wide range of available tools in a farm tools store. It's been an incredible journey, and I'm thrilled to showcase the result✨
0:50

Excited to share a glimpse of my first app with SwiftUI 😌. I've built from scratch a user-friendly ios app, empowering users to explore and examine the wide range of available tools in a farm tools store. It's been an incredible journey, and I'm thrilled to showcase the result✨

𝐁𝐨𝐝𝐦𝐚𝐧𝐮𝐞𝐥(❖,❖)

15,373 просмотров • 3 лет назад

Say goodbye to green screens! DiffusionMat is an AI framework that uses a diffusion model to create refined alpha mattes by correcting the output at every denoising step to look more like the original input image.
0:31

Say goodbye to green screens! DiffusionMat is an AI framework that uses a diffusion model to create refined alpha mattes by correcting the output at every denoising step to look more like the original input image.

Dreaming Tulpa 🥓👑

146,582 просмотров • 2 лет назад