Ming Lin

487 posts

Ming Lin

Ming Lin

@_minglin_

Web on Wearables @RealityLabs @Meta

New York, USA Katılım Ekim 2014
622 Takip Edilen304 Takipçiler
Sabitlenmiş Tweet
Ming Lin
Ming Lin@_minglin_·
Woo its launch day!! Today we shipped Web App Dev Mode and bringing the web stack to Meta Ray Ban Display. The #1 thing I get asked about wearables is “can I build an app for the glasses?”. Now you can and I’m proud to meet developers where they're at, on the web! Excited to see what the community builds. DM are open - let’s talk about web apps!
Meta for Developers@MetaforDevs

Developer Preview for Meta Ray-Ban Display is rolling out. 👓✨ Build web apps for display glasses with HTML, CSS, and JavaScript, or extend your mobile apps with the Meta Wearables Device Access Toolkit. Start building today 👉 bit.ly/49OzZNL

English
11
12
58
9.7K
Evan Bacon 🥓
Evan Bacon 🥓@Baconbrix·
@_minglin_ @razeenali01 I’d take a screenshot of it not working on my pair for the past few days but the option is missing. Have had to fully reset the device to get it working, but it goes away randomly.
English
1
0
0
82
Ming Lin
Ming Lin@_minglin_·
We're trying to build the largest wearables developer ecosystem. One way we're doing that is to make it as easy as possible to build glasses web app. Welcome Display Web App Simulator our growing suite of developer tools!
Oscar Falmer@OscarFalmer

📣 New Display Web App Simulator! This official Chrome extension recreates the display of Meta Ray-Ban Display in your browser, so you can preview and QA web apps against the real display rendering, additive blending, backgrounds and D-pad input. chromewebstore.google.com/detail/meta-ra…

English
0
0
9
1.1K
Ming Lin
Ming Lin@_minglin_·
one minute into the video and i want one
Iwahori Toshiki@iw_toshiki

【ペットとしてのドローン】 慶應義塾大学大学院メディアデザイン研究科の博士課程学生・徐銘陽らが開発したバルーンベースのソフト羽ばたき翼浮遊ドローン（UAV）「Cuddle-Fish」が屋内コンパニオン「SFR」（ソフト浮遊ロボット）として進化。インタラクションの可能性を追究する。#ドローン 《Floating Companion: Exploring Design Space for Soft Floating Robots in Indoor Environments》dl.acm.org/doi/10.1145/38…

English
0
0
1
199
thomas
thomas@c00kingwithai·
I met a girl today that didn’t use ai, she was my age and i wasn’t sure whether to think this girl is absolutely cooked or maybe she’s lowkey experiencing a different life us tech folks live
English
4
0
3
230
Ming Lin
Ming Lin@_minglin_·
@bnemehh comeback of the year!! seen it first hand
English
0
0
1
108
Bahij Nemeh
Bahij Nemeh@bnemehh·
6 months ago I was abusing Adderall and smoking a pack of cigarettes a day. Since then: - gone sober - lost 40lbs - hit 12.8% body fat Onward 🚀
Bahij Nemeh tweet media
English
9
1
22
864
joowon
joowon@n0w00j·
If you’re a creative not using AI you’re fcked. Introducing Melius: the world’s first creative canvas for agents. Here’s how it works:
English
380
159
2.1K
2.5M
thomas
thomas@c00kingwithai·
muse image
GIF
English
1
0
1
103
Filip Radenovic
Filip Radenovic@filipradenovic·
We released Muse Image and previewed Muse Video model today — first image and video generation models from Meta Superintelligence Labs 🧵
English
4
9
28
2.4K
Albert Pumarola
Albert Pumarola@AlbertPumarola·
🖼️Today, we’re introducing Muse Image! Muse Image pushes image generation toward a more agentic paradigm, with code execution, search-grounded reasoning, and self-refinement built into the generation loop. Honored to be part of this incredible team. ai.meta.com/blog/introduci…
Albert Pumarola tweet media
English
2
3
25
1.8K
Animesh Sinha
Animesh Sinha@_animeshsinha_·
Really excited to share Muse Image & Muse Video with everyone! This was a result of months of intense execution from teams in MSL. We hit #2 in image generation, #2 in single/multiple image editing, and #3 on video generation with this model on Arena. Muse Image is an agentic image generation model which can plan, perform tool calls, and do self-reflection to improve its own outputs. My favorite capability of the model is multi-reference image composition using search (give it a try!). The future trajectory looks strong as we see better results with more test-time compute. Try it out in Meta AI and Instagram today, and checkout the blog below for more details! Technical Blog: ai.meta.com/blog/introduci… Meta AI: meta.ai
English
6
2
37
2.1K
Ming Lin
Ming Lin@_minglin_·
@YKirstain congrats on the launch!! when muse image in wearables?
English
0
0
1
133
Yuval Kirstain
Yuval Kirstain@YKirstain·
Second example involves multi stage agentic planning and execution on a pretty complicated try-on request!
Yuval Kirstain tweet mediaYuval Kirstain tweet media
English
1
0
12
1.1K
Wenhu Chen
Wenhu Chen@WenhuChen·
🚀🚀
AI at Meta@AIatMeta

Introducing Muse Image and Muse Video, the first media generation models developed by Meta Superintelligence Labs. Muse Image is our most advanced image generation model yet. It follows instructions faithfully, edits with precision, composes from multiple references, and draws on Instagram for social context. It also brings agentic tool use capabilities to image generation and integrates with Muse Spark. You can try Muse Image in the Meta AI app and web, as well as in Instagram Stories and WhatsApp – starting in limited countries with more locations on the way. Today we’re also previewing Muse Video, which is built upon the same pretraining base as Muse Image to deliver exceptional visual fidelity with native audio support. Learn more about both models: go.meta.me/7f4427

ART
4
1
17
2.9K
Jiaming Song
Jiaming Song@baaadas·
Excited to help launch Muse Image / Video @AIatMeta. A few of my images are on the release page. Creation is moving from "one prompt -> one image" to iterative, agentic systems that plan, use tools, and refine. ai.meta.com/blog/introduci…
Jiaming Song tweet mediaJiaming Song tweet mediaJiaming Song tweet mediaJiaming Song tweet media
English
9
12
195
17.3K
Ming Lin
Ming Lin@_minglin_·
shout out @Meta MSL team!!
Arena.ai@arena

Exciting news: Meta’s Muse Image just claimed #2 in the Image Arena! Muse Image from @AIatMeta now ranks second only to OpenAI's GPT Image 2, outperforming Nano Banana, Grok Imagine, MAI Image, and many other leading image models. It holds #2 across the board: Text-to-Image, Single-Image Edit, and Multi-Image Edit. Congrats to the Meta team on this incredible milestone!

English
0
0
10
465

Keşfet

@SpaceXAI @Meta @Baconbrix @razeenali01 @c00kingwithai @bnemehh @n0w00j @thomas