Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

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 ➡️

AI at Meta

827,701 subscribers

1,617,795 views • 2 years ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

AI at Meta2 years 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 Meta2 years 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 Wrigley2 years ago

Legendary 7-day open source Meta run rn lfg

Lex Fridman2 years ago

Wow, amazing!

Dwayne2 years ago

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

rad ed2 years ago

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

Indra2 years 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 👑2 years ago

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

MindBranches2 years ago

Summary of the Meta SAM 2 announcement

Amit Shukla2 years 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 ➡️

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

97,755 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 ➡️

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 • 2 years 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 ➡️

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

186,348 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.

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

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:

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

190,934 views • 8 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

🚀 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

72,345 views • 1 year 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)

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

949,969 views • 3 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

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

324,599 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

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

186,560 views • 2 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 ➡️

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

1,234,744 views • 3 years 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)

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

TODAY WE LAUNCH SORA 2, THE WORLDS BEST VIDEO GENERATION MODEL feature you and your friends with raw real world physics, putting an end to the uncanny ai vibes let me show you how insane our model is, featuring me & sam altman:

TODAY WE LAUNCH SORA 2, THE WORLDS BEST VIDEO GENERATION MODEL feature you and your friends with raw real world physics, putting an end to the uncanny ai vibes let me show you how insane our model is, featuring me & sam altman:

gabriel

2,998,470 views • 10 months ago

Google DeepMind CEO Demis Hassabis says they will have AI agents that everyday consumers can use available later this year as the enabling capabilities, like a world model that can accurately model physics, are already present in their video model Veo 2

Google DeepMind CEO Demis Hassabis says they will have AI agents that everyday consumers can use available later this year as the enabling capabilities, like a world model that can accurately model physics, are already present in their video model Veo 2

Tsarathustra

35,184 views • 1 year ago

🎥 Our state-of-the-art video generation model Veo 2 is now available in YouTube Shorts. With the Dream Screen feature, creators can: ✨ Produce new clips that fit seamlessly into their storytelling with a quick text prompt ✨ Use it to make backgrounds for their videos. Here’s how →

🎥 Our state-of-the-art video generation model Veo 2 is now available in YouTube Shorts. With the Dream Screen feature, creators can: ✨ Produce new clips that fit seamlessly into their storytelling with a quick text prompt ✨ Use it to make backgrounds for their videos. Here’s how →

Google DeepMind

428,953 views • 1 year ago

SAM-2 is apache license - you can indeed just build crazy apps with them without fear. This weekend I ported SAM-2 models to run optimally on Apple Silicon. I have also quantized all the SAM models to 16bit, 8bit, and 4bit variants (collection below) Repo is open source and pip installable. Comes with all you'll need for interactive video segmentation - - bidirectional propagation, - positive and negative clicks, - bounding boxes, - streaming masks back to user, - lightweight fast-api server that you can extend I basically asked Codex to port over the original Facebook sam2 codebase to mlx and optimize it for mlx. And it just worked. This demo for example is a 4bit base-plus model (~100MB download) To speed up, you can also do spatial or temporal downsampling. That speeds inference on my old macbook by ~3x and the hit in parity is negligible.

SAM-2 is apache license - you can indeed just build crazy apps with them without fear. This weekend I ported SAM-2 models to run optimally on Apple Silicon. I have also quantized all the SAM models to 16bit, 8bit, and 4bit variants (collection below) Repo is open source and pip installable. Comes with all you'll need for interactive video segmentation - - bidirectional propagation, - positive and negative clicks, - bounding boxes, - streaming masks back to user, - lightweight fast-api server that you can extend I basically asked Codex to port over the original Facebook sam2 codebase to mlx and optimize it for mlx. And it just worked. This demo for example is a 4bit base-plus model (~100MB download) To speed up, you can also do spatial or temporal downsampling. That speeds inference on my old macbook by ~3x and the hit in parity is negligible.

AVB

17,363 views • 2 months ago

Introducing Odyssey-2 Pro—a frontier world model that generates long-running, interactive simulations in 720p! We're also launching the first world model API, to enable devs to build magical apps. We're now in the GPT-2 era of world models. Let the explosion of apps commence!

Introducing Odyssey-2 Pro—a frontier world model that generates long-running, interactive simulations in 720p! We're also launching the first world model API, to enable devs to build magical apps. We're now in the GPT-2 era of world models. Let the explosion of apps commence!

Odyssey

166,180 views • 6 months ago

Breaking: OpenAI just announced that their new AI image generator, DALL-E 3 will drop in October! 1. You can use it directly inside ChatGPT 2. It can create much better images of text than Midjourney 3. You can use the images commercially Check out this video shared by Sam Altman

Breaking: OpenAI just announced that their new AI image generator, DALL-E 3 will drop in October! 1. You can use it directly inside ChatGPT 2. It can create much better images of text than Midjourney 3. You can use the images commercially Check out this video shared by Sam Altman

Chase Lean

164,903 views • 2 years ago

In Prompt Engineering for Vision Models, taught by Abby Jacques Verre and Caleb Kaiser of Comet , you’ll learn how to prompt and fine-tune vision models for personalized image generation, image editing, object detection and segmentation. The prompts you'll use for vision models could be text, point coordinates, or bounding boxes, depending on the model. You'll also learn to tune hyperparameters to shape the output. Models you'll use include Segment-Anything Model (SAM), OWL-ViT, and Stable Diffusion. You'll also learn to fine-tune Stable Diffusion to generate personalized images (say, an image of a specific person), using a handful of images for training. As an example of a multi-step workflow, you'll use OWL-ViT to detect an object based on a text prompt, then pass the bounding box to SAM to create a segmentation mask, and input that mask into Stable Diffusion to replace the original object with a new one based on a text prompt. Controlling vision models can be tricky; this course will teach prompting and fine-tuning techniques to get precise control over their output. Get started here:

In Prompt Engineering for Vision Models, taught by Abby Jacques Verre and Caleb Kaiser of Comet , you’ll learn how to prompt and fine-tune vision models for personalized image generation, image editing, object detection and segmentation. The prompts you'll use for vision models could be text, point coordinates, or bounding boxes, depending on the model. You'll also learn to tune hyperparameters to shape the output. Models you'll use include Segment-Anything Model (SAM), OWL-ViT, and Stable Diffusion. You'll also learn to fine-tune Stable Diffusion to generate personalized images (say, an image of a specific person), using a handful of images for training. As an example of a multi-step workflow, you'll use OWL-ViT to detect an object based on a text prompt, then pass the bounding box to SAM to create a segmentation mask, and input that mask into Stable Diffusion to replace the original object with a new one based on a text prompt. Controlling vision models can be tricky; this course will teach prompting and fine-tuning techniques to get precise control over their output. Get started here:

Andrew Ng

151,198 views • 2 years ago

Today, we're introducing GLM-5.2 Fast: our GLM-5.2 Model API designed for the most demanding real-time use cases. The Fast tier delivers 2-3x higher TPS than the standard GLM-5.2 MAPI.

Today, we're introducing GLM-5.2 Fast: our GLM-5.2 Model API designed for the most demanding real-time use cases. The Fast tier delivers 2-3x higher TPS than the standard GLM-5.2 MAPI.

Baseten

113,008 views • 5 days ago