Loading video...

Video Failed to Load

Go Home

Introducing Meta Segment Anything Model 2 (SAM 2) — the first unified model for real-time, promptable object segmentation in images & videos. SAM 2 is available today under Apache 2.0 so that anyone can use it to build their own experiences Details ➡️

AIatMeta's profile picture

AI at Meta

810,883 subscribers

1,617,353 views • 1 year ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

10 Comments

AI at Meta's profile picture
AI at Meta1 year ago

In addition to the new model, we’re also releasing SA-V, a dataset that’s 4.5x larger + has ~53x more annotations than the largest existing video segmentation dataset. We hope this work will help accelerate new computer vision research ➡️

AI at Meta's profile picture
AI at Meta1 year ago

Like the original SAM, SAM 2 can be applied out of the box to a diverse range of real-world use cases and we’re excited to see what developers build with it. Try the demo ➡️ Get the code ➡️

Mckay Wrigley's profile picture
Mckay Wrigley1 year ago

Legendary 7-day open source Meta run rn lfg

Lex Fridman's profile picture
Lex Fridman1 year ago

Wow, amazing!

Dwayne's profile picture
Dwayne1 year ago

Wow. Meta are cooking gourmet Michelin star meals over here.

rad ed's profile picture
rad ed1 year ago

inpainting is about to go crazy when its added to video with persistent object detection

Indra's profile picture
Indra1 year ago

I like it. It's gonna save video editors a lot of time creating masks and rotoscoping. It's not perfect, but it saves us from Adobe CCs proprietary, lock-in roto tools. Thanks zucc.

mansa musa 👑's profile picture
mansa musa 👑1 year ago

This is wild! Advertisers are going to pay subscriptions to keep their products in videos lmao

MindBranches's profile picture
MindBranches1 year ago

Summary of the Meta SAM 2 announcement

Amit Shukla's profile picture
Amit Shukla1 year ago

Just when I thought I'm done reading 99 pages, you show up with another book. Grateful for the Apache license.

Related Videos

Segment Anything Model 2 (SAM 2) is a foundation model from Meta FAIR for promptable visual segmentation in images & videos. Available now for anyone to build on for free, open source under an Apache license. Try the demo ➡️
0:35

Segment Anything Model 2 (SAM 2) is a foundation model from Meta FAIR for promptable visual segmentation in images & videos. Available now for anyone to build on for free, open source under an Apache license. Try the demo ➡️

AI at Meta

97,733 views • 1 year ago

SAM 2 from Meta FAIR is the first unified model for real-time, promptable object segmentation in images & videos. Using the model in our web-based demo you can segment, track and apply effects to objects in video in just a few clicks. Try SAM 2 ➡️
0:40

SAM 2 from Meta FAIR is the first unified model for real-time, promptable object segmentation in images & videos. Using the model in our web-based demo you can segment, track and apply effects to objects in video in just a few clicks. Try SAM 2 ➡️

AI at Meta

88,918 views • 1 year ago

The Segment Anything Model (SAM) by Meta AI is a step toward the first foundation model for image segmentation. SAM is capable of one-click segmentation of any object from photos or videos + zero-shot transfer to other segmentation tasks. Try the demo ➡️
0:51

The Segment Anything Model (SAM) by Meta AI is a step toward the first foundation model for image segmentation. SAM is capable of one-click segmentation of any object from photos or videos + zero-shot transfer to other segmentation tasks. Try the demo ➡️

AI at Meta

186,324 views • 3 years ago

Big News! Meta just released Segment Anything, a new AI model that can "cut out" any object, in any image/video, with a single click. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks.
0:22

Big News! Meta just released Segment Anything, a new AI model that can "cut out" any object, in any image/video, with a single click. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks.

Lior Alexander

290,190 views • 3 years ago

The last stage of Segment-Anything-Model-2 (SAM-2) is filled with what look to be dead GELUs. It's a graveyard out there.
0:31

The last stage of Segment-Anything-Model-2 (SAM-2) is filled with what look to be dead GELUs. It's a graveyard out there.

Rudy Gilman

26,564 views • 1 year ago

Meet SAM 3, a unified model that enables detection, segmentation, and tracking of objects across images and videos. SAM 3 introduces some of our most highly requested features like text and exemplar prompts to segment all objects of a target category. Learnings from SAM 3 will help power new features in Instagram Edits and Vibes, bringing advanced segmentation capabilities directly to creators. 🔗 Learn more:
1:09

Meet SAM 3, a unified model that enables detection, segmentation, and tracking of objects across images and videos. SAM 3 introduces some of our most highly requested features like text and exemplar prompts to segment all objects of a target category. Learnings from SAM 3 will help power new features in Instagram Edits and Vibes, bringing advanced segmentation capabilities directly to creators. 🔗 Learn more:

AI at Meta

189,875 views • 7 months ago

🚀 Excited to share a new tutorial on how to detect buildings 🏘️using the Segment Anything Model 2 (SAM 2) with Segment-Geospatial! You can choose interactive segmentation or utilize a GeoJSON file with building centroids or bounding boxes to do automated building detection. 📹 Check out the video tutorial: 📓 Explore the notebook: #Geospatial #OpenSource #AI #MachineLearning
0:49

🚀 Excited to share a new tutorial on how to detect buildings 🏘️using the Segment Anything Model 2 (SAM 2) with Segment-Geospatial! You can choose interactive segmentation or utilize a GeoJSON file with building centroids or bounding boxes to do automated building detection. 📹 Check out the video tutorial: 📓 Explore the notebook: #Geospatial #OpenSource #AI #MachineLearning

Qiusheng Wu

71,967 views • 1 year ago

Today we're releasing ZONOS2, our next-generation real-time TTS model with high-fidelity voice cloning. ZONOS2 is the most expressive open-source TTS model, released under Apache 2.0 and available on Zyphra Cloud on AMD. 🧵
1:30

Today we're releasing ZONOS2, our next-generation real-time TTS model with high-fidelity voice cloning. ZONOS2 is the most expressive open-source TTS model, released under Apache 2.0 and available on Zyphra Cloud on AMD. 🧵

Zyphra

331,666 views • 18 days ago

this is huge news from Cursor, they've pulled of the impossible and turned their ai-wrapper into a in-destructible moat sam altman literally called it cursor's ai agent harness is available for anyone to build on, which means ai models are now a commodity > 1-time install and now anyone can run cursor's agent locally or via cloud. use any model (e.g. gpt 5.5) but with the added cursor harness that makes it 10X better. > its so good that 3 of cursors biggest competitors are embedding it into their products. > now cursor DOESN'T DEPEND on anthropic or openai. their own model (composer 2) competes directly! yesterday sam altman said the ai model and harness are one and the same and today cursor turned their harness into a self-owned moat fucking masterclass (coming from a former cursor / ai wrapper hater)
0:35

this is huge news from Cursor, they've pulled of the impossible and turned their ai-wrapper into a in-destructible moat sam altman literally called it cursor's ai agent harness is available for anyone to build on, which means ai models are now a commodity > 1-time install and now anyone can run cursor's agent locally or via cloud. use any model (e.g. gpt 5.5) but with the added cursor harness that makes it 10X better. > its so good that 3 of cursors biggest competitors are embedding it into their products. > now cursor DOESN'T DEPEND on anthropic or openai. their own model (composer 2) competes directly! yesterday sam altman said the ai model and harness are one and the same and today cursor turned their harness into a self-owned moat fucking masterclass (coming from a former cursor / ai wrapper hater)

Ejaaz

949,487 views • 2 months ago

MetaAI's SAM 2 struggles when things move fast or when there are crowded, fast-moving objects! Introducing SAMURAI: An adaptation of the Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory. 100% Open Source
0:40

MetaAI's SAM 2 struggles when things move fast or when there are crowded, fast-moving objects! Introducing SAMURAI: An adaptation of the Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory. 100% Open Source

Sumanth

324,580 views • 1 year ago

Microsoft's new Florence 2 is big for Computer Vision. It's a merge between Text and Vision. With a single prompt you can instruct the model to do CV tasks like captioning, object detection, grounding, and segmentation. The best part, it only uses a single backbone to handle everything. ▸ Excels in zero-shot performance ▸ Unified model for detection, captioning, etc. ▸ FLD-5B dataset: 5B+ annotations, 126M images ▸ New benchmarks (>5.5+) on COCO, ADE20K
0:27

Microsoft's new Florence 2 is big for Computer Vision. It's a merge between Text and Vision. With a single prompt you can instruct the model to do CV tasks like captioning, object detection, grounding, and segmentation. The best part, it only uses a single backbone to handle everything. ▸ Excels in zero-shot performance ▸ Unified model for detection, captioning, etc. ▸ FLD-5B dataset: 5B+ annotations, 126M images ▸ New benchmarks (>5.5+) on COCO, ADE20K

Lior Alexander

186,544 views • 2 years ago

Introducing AI Click powered by Segment Anything (SAM) for biological images, on Biodock. We’ve worked hard to make SAM much more useful for bio - read below to find out how!
0:44

Introducing AI Click powered by Segment Anything (SAM) for biological images, on Biodock. We’ve worked hard to make SAM much more useful for bio - read below to find out how!

Michael

57,576 views • 3 years ago

We believe an open approach is the right one for the development of today's Al models. Today, we’re releasing Llama 2, the next generation of Meta’s open source Large Language Model, available for free for research & commercial use. Details ➡️
0:49

We believe an open approach is the right one for the development of today's Al models. Today, we’re releasing Llama 2, the next generation of Meta’s open source Large Language Model, available for free for research & commercial use. Details ➡️

AI at Meta

1,234,438 views • 2 years ago

🔉 Introducing SAM Audio, the first unified model that isolates any sound from complex audio mixtures using text, visual, or span prompts. We’re sharing SAM Audio with the community, along with a perception encoder model, benchmarks and research papers, to empower others to explore new forms of expression and build applications that were previously out of reach. 🔗 Learn more:
1:09

🔉 Introducing SAM Audio, the first unified model that isolates any sound from complex audio mixtures using text, visual, or span prompts. We’re sharing SAM Audio with the community, along with a perception encoder model, benchmarks and research papers, to empower others to explore new forms of expression and build applications that were previously out of reach. 🔗 Learn more:

AI at Meta

1,249,322 views • 6 months ago

🚀 The GeoAI QGIS Plugin is here 🔥 You can run Moondream vision-language models, object detection, image segmentation (SAM 3), and even train your own geospatial segmentation model end-to-end. Website: GitHub: Short demo: Full video tutorial: #QGIS #GeoAI #SAM3 #Geospatial #DeepLearning #ComputerVision #OpenSource #Python
2:11

🚀 The GeoAI QGIS Plugin is here 🔥 You can run Moondream vision-language models, object detection, image segmentation (SAM 3), and even train your own geospatial segmentation model end-to-end. Website: GitHub: Short demo: Full video tutorial: #QGIS #GeoAI #SAM3 #Geospatial #DeepLearning #ComputerVision #OpenSource #Python

Qiusheng Wu

11,682 views • 6 months ago

Dream Machine from Luma AI is now available on Poe! Generate videos, animate images, and build your own custom video bots using this state-of-the-art generative video model. (1/2)
0:26

Dream Machine from Luma AI is now available on Poe! Generate videos, animate images, and build your own custom video bots using this state-of-the-art generative video model. (1/2)

Poe

24,455 views • 1 year ago

Excited to announce RF-DETR, the current SOTA for real-time object detection, fully open source and Apache 2.0 for the community. More to come but the repo and Colab notebook are available today for you to use
1:56

Excited to announce RF-DETR, the current SOTA for real-time object detection, fully open source and Apache 2.0 for the community. More to come but the repo and Colab notebook are available today for you to use

Roboflow

189,959 views • 1 year ago

oh my.. hows this even possible Meta just dropped SAM 3D, you can auto select any object in still image and.. turn them into high quality 3D model the model is free to download and test in playground link in comments
0:27

oh my.. hows this even possible Meta just dropped SAM 3D, you can auto select any object in still image and.. turn them into high quality 3D model the model is free to download and test in playground link in comments

el.cine

794,410 views • 7 months ago

we are introducing a state-of-the-art real-time object detection model, RF-DETR RF-DETR outperforms all existing object detection models on real world datasets and is the first real-time model to achieve 60+ Average Precision on COCO talked w/ NVIDIA about it at GTC:
2:31

we are introducing a state-of-the-art real-time object detection model, RF-DETR RF-DETR outperforms all existing object detection models on real world datasets and is the first real-time model to achieve 60+ Average Precision on COCO talked w/ NVIDIA about it at GTC:

Joseph Nelson

18,231 views • 1 year ago

Introducing Empathic Voice Interface 2 (EVI 2), our new voice-to-voice foundation model. EVI 2 merges language and voice into a single model trained specifically for emotional intelligence. You can try it and start building today.
8:06

Introducing Empathic Voice Interface 2 (EVI 2), our new voice-to-voice foundation model. EVI 2 merges language and voice into a single model trained specifically for emotional intelligence. You can try it and start building today.

Hume AI

165,616 views • 1 year ago