Loading video...

Video Failed to Load

Go Home

Moondream 3: world's best open-vocab object detection, packed in a fast, open model.

moondreamai's profile picture

moondream

10,274 subscribers

52,595 views • 11 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Moondream doesn’t just OCR, it understands. Full JSON receipts, instant Q&A. Open, tiny, blazingly fast.
0:10

Moondream doesn’t just OCR, it understands. Full JSON receipts, instant Q&A. Open, tiny, blazingly fast.

moondream

280,580 views • 10 months ago

wow.. this new object detection AI tool is incredible and open sourced link in comment
0:14

wow.. this new object detection AI tool is incredible and open sourced link in comment

el.cine

214,745 views • 1 year ago

Train a TensorFlow object detection model – then deploy it on a robot 🤖 Iulia Feroli (Iulia Feroli) shows how to turn a notebook into a real-time object detection app. This tutorial works for any project – though we demonstrate the deployment on (and assisted by!) the #ReachyMini, an open-source robot from Pollen Robotics. Built with PyCharm + Claude Code. 👉 Watch it in action:
0:17

Train a TensorFlow object detection model – then deploy it on a robot 🤖 Iulia Feroli (Iulia Feroli) shows how to turn a notebook into a real-time object detection app. This tutorial works for any project – though we demonstrate the deployment on (and assisted by!) the #ReachyMini, an open-source robot from Pollen Robotics. Built with PyCharm + Claude Code. 👉 Watch it in action:

PyCharm, a JetBrains IDE

34,908 views • 3 months ago

GLM-5 is live on 0G Compute. 744B parameters. SOTA open-source. MIT license. Beats GPT-5.2 on BrowseComp and Terminal-Bench. Run the world's best open model on decentralized infrastructure. No cloud vendor. No data logging. No ToS surprises. Your prompts stay yours.
0:14

GLM-5 is live on 0G Compute. 744B parameters. SOTA open-source. MIT license. Beats GPT-5.2 on BrowseComp and Terminal-Bench. Run the world's best open model on decentralized infrastructure. No cloud vendor. No data logging. No ToS surprises. Your prompts stay yours.

0G Labs (Home of Infinite AI)

79,118 views • 6 months ago

Object detection + tracking + counting using Ultralytics YOLO26 🚀 👉 Object detection tells you what is in a scene. 👉 Tracking follows each object across video frames. 👉 Counting turns those movements into actionable data. YOLO26 delivers fast, accurate detections, while multi-object tracking maintains unique identities across frames. Add configurable counting lines or regions to measure entries, exits, directional movement, and other real-world traffic metrics. #vehicles #MachineLearning #Highway
0:12

Object detection + tracking + counting using Ultralytics YOLO26 🚀 👉 Object detection tells you what is in a scene. 👉 Tracking follows each object across video frames. 👉 Counting turns those movements into actionable data. YOLO26 delivers fast, accurate detections, while multi-object tracking maintains unique identities across frames. Add configurable counting lines or regions to measure entries, exits, directional movement, and other real-world traffic metrics. #vehicles #MachineLearning #Highway

Muhammad Rizwan Munawar

16,069 views • 29 days ago

The entire defense crowds to Luka leaving a wide open Luke Kennard The best 3-PT shooter in the league being this open is UNFAIR 😭😭
0:16

The entire defense crowds to Luka leaving a wide open Luke Kennard The best 3-PT shooter in the league being this open is UNFAIR 😭😭

LakersMuse

79,271 views • 6 months ago

dangerous open-source models 💣 made in ComfyUI and Adobe After Effects with Wan 2.2 I2V + T2V + Vace / Krea 2 / GPT Image 2.0 / SYSTMS TimeSlice + HUD / Moondream 2
0:13

dangerous open-source models 💣 made in ComfyUI and Adobe After Effects with Wan 2.2 I2V + T2V + Vace / Krea 2 / GPT Image 2.0 / SYSTMS TimeSlice + HUD / Moondream 2

Ingi Erlingsson 🪄

30,990 views • 1 month ago

Meta's SAM 3 is a beast. before: collect data, train custom object detector, use tracker to estimate object motion - days now: track anything with text prompt - seconds real-time object detection will never be the same.
0:15

Meta's SAM 3 is a beast. before: collect data, train custom object detector, use tracker to estimate object motion - days now: track anything with text prompt - seconds real-time object detection will never be the same.

Akshay 🚀

31,461 views • 9 months ago

The host course for the 2026 U.S. Women's Open will welcome the world's best for the LA28 Olympic Games! ⛳️
0:11

The host course for the 2026 U.S. Women's Open will welcome the world's best for the LA28 Olympic Games! ⛳️

NBC Olympics & Paralympics

26,852 views • 2 months ago

The world's tallest bridge is scheduled to open on September 28 in Guizhou, China.
0:19

The world's tallest bridge is scheduled to open on September 28 in Guizhou, China.

Li Zexin 李泽欣

20,850 views • 11 months ago

go my puppetlings from fnaf 2 movie (model by Benji COMMS OPEN (1/3))
0:15

go my puppetlings from fnaf 2 movie (model by Benji COMMS OPEN (1/3))

Coda

279,687 views • 9 months ago

Crimson Desert has the best Open-World in any game. It may not be the best open-world game but it tops in the sense of adventure it produces through it's open-world.
0:14

Crimson Desert has the best Open-World in any game. It may not be the best open-world game but it tops in the sense of adventure it produces through it's open-world.

SpawnYaard 🎮

14,572 views • 4 months ago

Best way to open a coconut
0:10

Best way to open a coconut

The Future of Agriculture

511,203 views • 2 months ago

Stable Audio 3 by Stability AI is just out It mainly comes with 3 open source variants: - Stable Audio 3 Medium (2B) - Stable Audio 3 Small (0.6B) - Music - Stable Audio 3 Small (0.6B) - VFX (and a "large" closed variant) The open models are really fast and high quality
0:14

Stable Audio 3 by Stability AI is just out It mainly comes with 3 open source variants: - Stable Audio 3 Medium (2B) - Stable Audio 3 Small (0.6B) - Music - Stable Audio 3 Small (0.6B) - VFX (and a "large" closed variant) The open models are really fast and high quality

apolinario (poli)

41,568 views • 3 months ago

there's no catch; SAM3 is open source and really good one of the things it does really well is object tracking, even in crazy complex scenes like basketball probably my favorite computer vision model ever
0:18

there's no catch; SAM3 is open source and really good one of the things it does really well is object tracking, even in crazy complex scenes like basketball probably my favorite computer vision model ever

SkalskiP

1,476,623 views • 3 months ago

Good to know: MinMax-M2 is one of the best model at UI design 👀 (it’s open source!)
0:13

Good to know: MinMax-M2 is one of the best model at UI design 👀 (it’s open source!)

Victor M

36,124 views • 9 months ago

Paolo Banchero AIRBALLED a wide-open 3 and MISSED a wide-open dunk 😭
0:13

Paolo Banchero AIRBALLED a wide-open 3 and MISSED a wide-open dunk 😭

Logion Noops

471,718 views • 7 months ago

Introducing Find the best local models based on real data 1. People run and submit benchmarks 2. Stats aggregated over models / devices 3. Find the best model for you `npx whatcanirun`, fully open-source
0:16

Introducing Find the best local models based on real data 1. People run and submit benchmarks 2. Stats aggregated over models / devices 3. Find the best model for you `npx whatcanirun`, fully open-source

⁵⁄₉

133,567 views • 4 months ago