Loading video...

Video Failed to Load

Go Home

I need to annotate some images for training a computer vision model. There are many powerful annotation platforms available, but I want to keep my images local. I added a new section to my CV Streamlit app to quickly annotate images and train a YOLO model in a few clicks.

mfranz_on's profile picture

Marco Franzon

14,737 subscribers

29,530 views • 6 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

We just released Firefly Custom Models (beta) to everyone 🎉 You can train a model on your own images to keep a consistent style or character! I trained a model on my photography and generated images that would be impossible to get any other way for my upcoming film.
0:32

We just released Firefly Custom Models (beta) to everyone 🎉 You can train a model on your own images to keep a consistent style or character! I trained a model on my photography and generated images that would be impossible to get any other way for my upcoming film.

Kris Kashtanova

26,766 views • 4 months ago

Open sourcing InScene + InScene Annotate - a pair of LoRAs for steering in-scene image generation w/ QwenEdit. You can use a combination of prompts + annotations to generate consistent images inside a scene. In beta but v. powerful. Model + workflow below, training data soon.
0:58

Open sourcing InScene + InScene Annotate - a pair of LoRAs for steering in-scene image generation w/ QwenEdit. You can use a combination of prompts + annotations to generate consistent images inside a scene. In beta but v. powerful. Model + workflow below, training data soon.

POM

71,441 views • 8 months ago

Circus Momma Model Showcase A simple model showcase animation I made a while ago that I added a small twist to. Model by AnthonyBlender Ported by Rccke If you enjoy this, come join my Patreon to see more content plus some exclusive images as well!
0:30

Circus Momma Model Showcase A simple model showcase animation I made a while ago that I added a small twist to. Model by AnthonyBlender Ported by Rccke If you enjoy this, come join my Patreon to see more content plus some exclusive images as well!

Ignition Of Change 🔞 (3/2)

10,860 views • 3 years ago

I wanted to make a titantron for my retro Lita but I didn't want to use too many images so I made a WWF No Mercy 64 style one 💀
0:53

I wanted to make a titantron for my retro Lita but I didn't want to use too many images so I made a WWF No Mercy 64 style one 💀

JobberGames

17,368 views • 4 months ago

I needed an app to export markdown from images and PDFs, so I built one using the best model on the market: Mistral OCR. It can convert images, PDFs, and even extract tables and images, keeping them contextually within the markdown. All you need is a Mistral AI API.
1:15

I needed an app to export markdown from images and PDFs, so I built one using the best model on the market: Mistral OCR. It can convert images, PDFs, and even extract tables and images, keeping them contextually within the markdown. All you need is a Mistral AI API.

Pietro Schirano

48,786 views • 1 year ago

i trained a computer vision model to count chinups roboflow rapid + SAM3 detected the chinup bar - hands - head through natural language prompts then I wrote a python script to count completed reps (head above bar) and annotate the video idea for a gamified fitness app? automated tracking of your workout, with rep counts per exercise added to your database. this gives progress stats over time, and a leaderboard with your friends these new vision models are neat because they can detect exercise equipment, allowing tracking of dumbbell workouts, bench press, squat, etc.
0:30

i trained a computer vision model to count chinups roboflow rapid + SAM3 detected the chinup bar - hands - head through natural language prompts then I wrote a python script to count completed reps (head above bar) and annotate the video idea for a gamified fitness app? automated tracking of your workout, with rep counts per exercise added to your database. this gives progress stats over time, and a leaderboard with your friends these new vision models are neat because they can detect exercise equipment, allowing tracking of dumbbell workouts, bench press, squat, etc.

AA

1,180,630 views • 7 months ago

updated tile buddy! my app for tiling repeating patterns. I use this to create background images for my videos, but its also great for wallpapers! I added some features to download common sizes, and snap to closest tile size, so backgrounds still repeat
0:43

updated tile buddy! my app for tiling repeating patterns. I use this to create background images for my videos, but its also great for wallpapers! I added some features to download common sizes, and snap to closest tile size, so backgrounds still repeat

Wes Bos

13,768 views • 3 months ago

Been using Glaze for a few weeks to make personal tools and its so incredibly slick. Made this image converter today that watches folders and converts / resizes any images added to it based on some rules. Something only I need, tailored to my exact workflow.
0:29

Been using Glaze for a few weeks to make personal tools and its so incredibly slick. Made this image converter today that watches folders and converts / resizes any images added to it based on some rules. Something only I need, tailored to my exact workflow.

Dan Hollick

105,421 views • 4 months ago

im a vtuber and i know im not the only one addicted to arm toggles... and i added so many arms to my customizable model 😭 these are some of my current faves, but there are plenty more WIPs on the way 🥰 #live2D ⁠#MidnightMoshieModel
0:21

im a vtuber and i know im not the only one addicted to arm toggles... and i added so many arms to my customizable model 😭 these are some of my current faves, but there are plenty more WIPs on the way 🥰 #live2D ⁠#MidnightMoshieModel

✦ Moshie 🧷🦈 モシ 𓆩♡𓆪 CUSTOM MODEL OUT NOW

58,954 views • 2 months ago

I created a 3D Gaussian Splat of my kitchen using 1/3rd the images it used to take me by using NVIDIA AI Developer's 3DGRUT! I can now use 180 degree fisheye images and ray tracing to make detailed splats. The only reason the scene isn't sharper is because my input images weren't super sharp - when I took the images back in October, I was still learning to use the lens. I plan to make a "first reactions/overview video". Tutorial after that. For reference, this took 206 images and the ultrawide on my iPhone took 608 images to capture. #3D #AEC #Computervision
0:40

I created a 3D Gaussian Splat of my kitchen using 1/3rd the images it used to take me by using NVIDIA AI Developer's 3DGRUT! I can now use 180 degree fisheye images and ray tracing to make detailed splats. The only reason the scene isn't sharper is because my input images weren't super sharp - when I took the images back in October, I was still learning to use the lens. I plan to make a "first reactions/overview video". Tutorial after that. For reference, this took 206 images and the ultrawide on my iPhone took 608 images to capture. #3D #AEC #Computervision

Jonathan Stephens

30,663 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

186,560 views • 2 years ago

I mentioned that I need a lot of help in my prayers because I tend to wander, and these images really help me! Here’s two I have close to my rocker. The Good Newsroom
1:17

I mentioned that I need a lot of help in my prayers because I tend to wander, and these images really help me! Here’s two I have close to my rocker. The Good Newsroom

Cardinal Dolan

18,682 views • 1 month ago

Here's a cool workflow! I used Perplexity to do Deep Research on how to optimize HGH levels. I put the output into Notebook LM to create a podcast & used Grok to create two podcast persona images. Then, loaded the audio & images into Hedra' new Character 3 model.
2:13

Here's a cool workflow! I used Perplexity to do Deep Research on how to optimize HGH levels. I put the output into Notebook LM to create a podcast & used Grok to create two podcast persona images. Then, loaded the audio & images into Hedra' new Character 3 model.

Blaine Brown

159,079 views • 1 year ago

Having humans annotate data to pre-train robots is expensive and time-consuming! Introducing SPRINT: A pre-training approach using LLMs and offline RL to equip robots w/ many language-annotated skills while minimizing human annotation effort! URL: 🧵👇
1:22

Having humans annotate data to pre-train robots is expensive and time-consuming! Introducing SPRINT: A pre-training approach using LLMs and offline RL to equip robots w/ many language-annotated skills while minimizing human annotation effort! URL: 🧵👇

Jesse Zhang @ ICML 2026 ✈️

24,665 views • 3 years ago

🚀Excited to share that #Gemini 3 Flash can do code execution on images to zoom, count, and annotate visual inputs! The model can choose when to write code to: 🔍 Zoom & Inspect: Detect when details are too small and zoom-in. 🧮 Compute Visually: Run multi-step calculations using code (e.g., summing line items on a receipt). ✏️ Annotate: Draw arrows or bounding boxes to answer questions or show relationships between objects.
1:35

🚀Excited to share that #Gemini 3 Flash can do code execution on images to zoom, count, and annotate visual inputs! The model can choose when to write code to: 🔍 Zoom & Inspect: Detect when details are too small and zoom-in. 🧮 Compute Visually: Run multi-step calculations using code (e.g., summing line items on a receipt). ✏️ Annotate: Draw arrows or bounding boxes to answer questions or show relationships between objects.

Fei Xia

19,284 views • 7 months ago

Microsoft is testing powerful AI features in the Windows 11 Paint app to turn images into short animations and edit images using a prompt.
0:47

Microsoft is testing powerful AI features in the Windows 11 Paint app to turn images into short animations and edit images using a prompt.

Pirat_Nation 🔴

44,930 views • 9 months ago

The LVM (large vision model) revolution is coming a little after the LLM (large language model) one, and will transform how we process images. But there’s an important difference between LVMs and LLMs: - Internet text is similar enough to proprietary text documents that an LLM trained on internet text can understand your documents. - But internet images – such as Instagram pictures – contain a lot of pictures of people, pets, landmarks, and everyday objects. Many practical vision applications (manufacturing, aerial imagery, life sciences, etc.) use images that look nothing like most internet images. So a generic LVM trained on internet images fares poorly at picking out the most salient features of images in many specialized domains. That’s why domain specific LVMs – ones adapted to images of a particular domain (such as semiconductor manufacturing, or pathology) – do much better. At LandingAI , by using ~100K unlabeled images to adapt an LVM to a specific domain, we see significantly improved results, for example where only 10-30% as much labeled data is now needed to achieve a certain level of performance. For companies with large sets of images that look nothing like internet images, I think domain specific LVMs can be a way to unlock considerable value from their data. Dan Maloney and I share more details in the video.
3:55

The LVM (large vision model) revolution is coming a little after the LLM (large language model) one, and will transform how we process images. But there’s an important difference between LVMs and LLMs: - Internet text is similar enough to proprietary text documents that an LLM trained on internet text can understand your documents. - But internet images – such as Instagram pictures – contain a lot of pictures of people, pets, landmarks, and everyday objects. Many practical vision applications (manufacturing, aerial imagery, life sciences, etc.) use images that look nothing like most internet images. So a generic LVM trained on internet images fares poorly at picking out the most salient features of images in many specialized domains. That’s why domain specific LVMs – ones adapted to images of a particular domain (such as semiconductor manufacturing, or pathology) – do much better. At LandingAI , by using ~100K unlabeled images to adapt an LVM to a specific domain, we see significantly improved results, for example where only 10-30% as much labeled data is now needed to achieve a certain level of performance. For companies with large sets of images that look nothing like internet images, I think domain specific LVMs can be a way to unlock considerable value from their data. Dan Maloney and I share more details in the video.

Andrew Ng

684,989 views • 2 years ago

a video of all of those last images because I worked on them in the same file at various times. My files are a labyrinth of random images in many stages of WIP song simply because I can't stop listening to it since watching Barbarian
2:11

Sensitive content

a video of all of those last images because I worked on them in the same file at various times. My files are a labyrinth of random images in many stages of WIP song simply because I can't stop listening to it since watching Barbarian

ol scratch

21,636 views • 3 years ago

Ask and you shall receive: our beloved doodle feature is officially available in Flow! Just tap the pencil icon on any of your images. From there, you can draw, type, or annotate to your heart's desire. Finally, a simple prompt like, "follow the instructions in my annotations, then remove my annotations" will bring your masterpiece to life.
0:57

Ask and you shall receive: our beloved doodle feature is officially available in Flow! Just tap the pencil icon on any of your images. From there, you can draw, type, or annotate to your heart's desire. Finally, a simple prompt like, "follow the instructions in my annotations, then remove my annotations" will bring your masterpiece to life.

Google Flow

34,362 views • 9 months ago