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.

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

805,973 subscribers

97,730 views • 1 year ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

Mikameel ᯅ1 year ago

We used SAM for segmenting comic books and extract layers to add depth.

Alvar Laigna 𝕏 💙 𝕏1 year ago

@codegurusblog This is great! I’am already building on that. Lovely! #marketing #Meta #AI

ren simmons1 year ago

Even on a real-time video feed

Tony Jose Matos1 year ago

Inject this into @dingboard_ plz rn 😩

عراقيون 🇮🇶1 year ago

My @Facebook account was hacked by an unknown person. He changed the email, password, and phone number, and I cannot access my account currently. Please help me in recovering the account and I am ready to prove other means of ownership of my account, waiting for your response..

moonbi 🇪🇺🪢1 year ago

Can we track the objects like count it with python ?

Lindsay Richman1 year ago

We (@InnerverseAI) will try this out! 🦸🏻‍♀️

Use Your AI1 year ago

Wonderful. Hope it works in production as well. We will try it and update you. Follow us for the results.

GPT.Biz1 year ago

This open-source tool looks perfect for anyone diving into visual segmentation. Worth checking out!

Glintz AI1 year ago

Artificial intelligence unfolds like a fractal mirror maze, where consciousness fades into an abyss of self-referential algorithms. 🧐

Related Videos

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 ➡️

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

1,617,216 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 • 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 ➡️

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

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

324,545 views • 1 year ago

SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware check out this SAM2 vs SAMURAI comparison! - paper: - code: - license: Apache-2.0

SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware check out this SAM2 vs SAMURAI comparison! - paper: - code: - license: Apache-2.0

SkalskiP

124,358 views • 1 year 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

1,234,383 views • 2 years ago

Gemini 2.5 Browser Use model is now available on Browserbase for anyone to try for free. Testing time 👀

Gemini 2.5 Browser Use model is now available on Browserbase for anyone to try for free. Testing time 👀

TestingCatalog News 🗞

55,165 views • 8 months ago

Llama 2 (7B, 13B and 70B) is now available in Lit-GPT! 🚀 Try running inference on the chat model or finetune the foundation model ➡️ #Llama2 #MachineLearning #opensource

Llama 2 (7B, 13B and 70B) is now available in Lit-GPT! 🚀 Try running inference on the chat model or finetune the foundation model ➡️ #Llama2 #MachineLearning #opensource

Lightning AI ⚡️

17,845 views • 2 years ago

Apache 2.0 license🔥 On-device deployment ready Extends SAM2 for tracking objects in videos 🔥 Click-to-segment support EdgeTAM by Meta !

Apache 2.0 license🔥 On-device deployment ready Extends SAM2 for tracking objects in videos 🔥 Click-to-segment support EdgeTAM by Meta !

Gradio

23,301 views • 1 year ago

📦 Fully open-source under Apache 2.0 — the FULL stack: ✅ Base model (256p) ✅ Distilled model ✅ Super-resolution model (540p & 1080p) ✅ Inference code 🤗 Models: 🎮 Demo: 💻 Code: 📄 Paper: More videos below! Go build something amazing 🚀

📦 Fully open-source under Apache 2.0 — the FULL stack: ✅ Base model (256p) ✅ Distilled model ✅ Super-resolution model (540p & 1080p) ✅ Inference code 🤗 Models: 🎮 Demo: 💻 Code: 📄 Paper: More videos below! Go build something amazing 🚀

Pengfei Liu

11,927 views • 2 months ago

I'm genius. Launching Falafel, a free open-source plugin for Davinci resolve powered by @FAL . Now you can generate videos from images right from your video editor. In this launch, only Wan 2.2 model is supported.

I'm genius. Launching Falafel, a free open-source plugin for Davinci resolve powered by @FAL . Now you can generate videos from images right from your video editor. In this launch, only Wan 2.2 model is supported.

anshuman

20,239 views • 10 months ago

New release from Meta FAIR — Meta Motivo is a first-of-its-kind behavioral foundation model for controlling virtual physics-based humanoid agents for a wide range of complex whole-body tasks. The model is capable of expressing human-like behaviors and achieves performance competitive with task-specific methods and outperforms state-of-the-art unsupervised RL and model-based baselines. Try the demo ➡️ Get the model and code ➡️ We’re excited about how this research could pave the way for fully embodied agents, leading to more lifelike NPCs, democratization of character animation and new types of immersive experiences.

New release from Meta FAIR — Meta Motivo is a first-of-its-kind behavioral foundation model for controlling virtual physics-based humanoid agents for a wide range of complex whole-body tasks. The model is capable of expressing human-like behaviors and achieves performance competitive with task-specific methods and outperforms state-of-the-art unsupervised RL and model-based baselines. Try the demo ➡️ Get the model and code ➡️ We’re excited about how this research could pave the way for fully embodied agents, leading to more lifelike NPCs, democratization of character animation and new types of immersive experiences.

AI at Meta

129,055 views • 1 year ago

Oh I need this model in my OpenClaw! SoulX-Singer, a great zero-shot singing voice synthesis model has been released on Hugging Face Apache 2 license as well! Check out the demo: And the model:

Oh I need this model in my OpenClaw! SoulX-Singer, a great zero-shot singing voice synthesis model has been released on Hugging Face Apache 2 license as well! Check out the demo: And the model:

Tiezhen WANG

21,622 views • 4 months ago

New from Meta FAIR: Code World Model (CWM), a 32B-parameter research model designed to explore how world models can transform code generation and reasoning about code. We believe in advancing research in world modeling and are sharing CWM under a research license to help empower the community to build upon our work. ➡️ Read the technical report: ➡️Download the open weights: ➡️Download the code:

New from Meta FAIR: Code World Model (CWM), a 32B-parameter research model designed to explore how world models can transform code generation and reasoning about code. We believe in advancing research in world modeling and are sharing CWM under a research license to help empower the community to build upon our work. ➡️ Read the technical report: ➡️Download the open weights: ➡️Download the code:

AI at Meta

312,889 views • 8 months ago

GLM-5, the latest frontier open model from Z.ai, is available now on Modal. We partnered with to release an endpoint that will be free for a limited time.

GLM-5, the latest frontier open model from Z.ai, is available now on Modal. We partnered with to release an endpoint that will be free for a limited time.

Modal

58,785 views • 4 months ago

Meet MoshiVis🎙️🖼️, the first open-source real-time speech model that can talk about images! It sees, understands, and talks about images — naturally, and out loud. Voice interaction with a compact model endowed with visual understanding opens up new applications, from audio description for the visual impaired to visual access to information. Try it out 👉 Blog post 👉

Meet MoshiVis🎙️🖼️, the first open-source real-time speech model that can talk about images! It sees, understands, and talks about images — naturally, and out loud. Voice interaction with a compact model endowed with visual understanding opens up new applications, from audio description for the visual impaired to visual access to information. Try it out 👉 Blog post 👉

kyutai

47,924 views • 1 year ago

Introducing the Describe Anything Model (DAM), a powerful Multimodal LLM that generates detailed descriptions for user-specified regions in images or videos using points, boxes, scribbles, or masks. Open-source code, models, demo, data, and benchmark at:

Introducing the Describe Anything Model (DAM), a powerful Multimodal LLM that generates detailed descriptions for user-specified regions in images or videos using points, boxes, scribbles, or masks. Open-source code, models, demo, data, and benchmark at:

Yin Cui

34,975 views • 1 year ago

A closer look at the evolution of the research from Meta FAIR that led to our latest open source work for human-robot collaboration. Details on Meta PARTNR ➡️

A closer look at the evolution of the research from Meta FAIR that led to our latest open source work for human-robot collaboration. Details on Meta PARTNR ➡️

AI at Meta

41,228 views • 1 year 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.

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

🚨 FASHN VTON v1.5 is now open source. Released in early 2025 and still widely used, this virtual try-on model generates photorealistic images from a person image and a garment image. Key points: • Pixel-space RGB generation, no VAE • Maskless inference, no person segmentation needed • 972M parameters, ~5s on H100, runs on consumer GPUs • Apache 2.0 licensed, first commercially usable open-source VTON Why open source? While the industry moves toward massive generalist models, FASHN VTON v1.5 proves a focused alternative. This is a production-grade virtual try-on model you can train for $5–10k, own, study, and extend. Built for researchers, developers, and fashion tech teams who want more than black-box APIs. More info in the comments.

🚨 FASHN VTON v1.5 is now open source. Released in early 2025 and still widely used, this virtual try-on model generates photorealistic images from a person image and a garment image. Key points: • Pixel-space RGB generation, no VAE • Maskless inference, no person segmentation needed • 972M parameters, ~5s on H100, runs on consumer GPUs • Apache 2.0 licensed, first commercially usable open-source VTON Why open source? While the industry moves toward massive generalist models, FASHN VTON v1.5 proves a focused alternative. This is a production-grade virtual try-on model you can train for $5–10k, own, study, and extend. Built for researchers, developers, and fashion tech teams who want more than black-box APIs. More info in the comments.

FASHN AI

19,065 views • 4 months ago