HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
facebookresearch
segment-anything
Jupyter Notebook2023–2024
facebookresearch / segment-anything

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

AI & Machine Learning
Explore on GitHubRead Hacker News discussions
21Distinct people
24Mentions
1Explicit recommenders
55.1KGitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

GitHub

Where it is used

No documented product use was verified in the last source check.

What people are saying

Yeah, they are great and some of the reason (up the causal chain) for some of the work I've done! Seems really fun! <3 :)))) Facebook's Segment Anything Model I think has a lot…

tysam_and used a recommendation phrase. One indexed comment matches. This is a phrase match, not a verdict.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 3:56:07 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by month24 dated mentions

Observed mentions: 2023-04-05 13:26:52 UTC to 2024-06-04 15:22:31 UTC.

0510152023-04-01 00:00:00 UTC to 2023-05-01 00:00:00 UTC (exclusive): 17 mentions; 2 submissions, 15 commentsApr 20232023-05-01 00:00:00 UTC to 2023-06-01 00:00:00 UTC (exclusive): 2 mentions; 0 submissions, 2 comments2023-06-01 00:00:00 UTC to 2023-07-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-07-01 00:00:00 UTC to 2023-08-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-08-01 00:00:00 UTC to 2023-09-01 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2023-09-01 00:00:00 UTC to 2023-10-01 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2023-10-01 00:00:00 UTC to 2023-11-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-11-01 00:00:00 UTC to 2023-12-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsNov 20232023-12-01 00:00:00 UTC to 2024-01-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2024-01-01 00:00:00 UTC to 2024-02-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2024-02-01 00:00:00 UTC to 2024-03-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2024-03-01 00:00:00 UTC to 2024-04-01 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2024-04-01 00:00:00 UTC to 2024-05-01 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2024-05-01 00:00:00 UTC to 2024-06-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2024-06-01 00:00:00 UTC to 2024-07-01 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 commentsJun 2024

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Apr 20232023-04-01 00:00:00 UTC2023-05-01 00:00:00 UTC17215
May 20232023-05-01 00:00:00 UTC2023-06-01 00:00:00 UTC202
Jun 20232023-06-01 00:00:00 UTC2023-07-01 00:00:00 UTC000
Jul 20232023-07-01 00:00:00 UTC2023-08-01 00:00:00 UTC000
Aug 20232023-08-01 00:00:00 UTC2023-09-01 00:00:00 UTC101
Sep 20232023-09-01 00:00:00 UTC2023-10-01 00:00:00 UTC101
Oct 20232023-10-01 00:00:00 UTC2023-11-01 00:00:00 UTC000
Nov 20232023-11-01 00:00:00 UTC2023-12-01 00:00:00 UTC000
Dec 20232023-12-01 00:00:00 UTC2024-01-01 00:00:00 UTC000
Jan 20242024-01-01 00:00:00 UTC2024-02-01 00:00:00 UTC000
Feb 20242024-02-01 00:00:00 UTC2024-03-01 00:00:00 UTC000
Mar 20242024-03-01 00:00:00 UTC2024-04-01 00:00:00 UTC101
Apr 20242024-04-01 00:00:00 UTC2024-05-01 00:00:00 UTC101
May 20242024-05-01 00:00:00 UTC2024-06-01 00:00:00 UTC000
Jun 20242024-06-01 00:00:00 UTC2024-07-01 00:00:00 UTC110

What Hacker News says

24 sources
Fengjiao·Jun 4, 2024Submission

Show HN: Shortbread App – AI-powered, romantic comics for women

Hi HN! Fengjiao and Evan here. We are building Shortbread App, Netflix for webcomics. We publish guilty-pleasure romance series (think 50 Shades of Gray) as comics. Like the mature version of Webtoon. You can see two comics episodes at https://create.shortbread.ai/viewer/3d25370c-a4eb-4df4-af8e-... https://create.shortbread.ai/viewer/866c2873-9962-4ebe-8f0c-..., and read more in the app via https://www.shortbreadapp.com/. All comics in the app are made by artists using the Shortbread AI Comics Studio (https://shortbread.ai). It is a powerful Photoshop-like editor that speeds up comic creation 10x with AI. The editor provides consistency and granular artistic control. More below. We first posted on HN 6 months ago when we built a prompt-to-comics AI (https://news.ycombinator.com/item?id=37792444). We sunsetted this soon after - it was a fu
Read the rest
n experiment but it didn’t meet the real need of comic artists. Shortbread Studio now changes this by enhancing how creators naturally work instead of replacing them. The tech: One-shot Character LoRA: Artists upload a single photo of their character. Our backend uses prompt engineering and ControlNet pipelines to generate a synthetic dataset from this photo. This dataset shows the character in all kinds of angles, poses and facial expressions that the artist can pick the best from. It’s then sent to our LoRA training service to create a LoRA model. This takes about 7 minutes. Control -> Redraw -> Refine Workflow: In real life drawing, you draw, erase, and draw again. The human creative process is iterative. In Shortbread Studio, artists can start from a text prompt, a sketch, a web image or a pose reference as a basis, create an initial panel and quickly modify and regenerate until they get what they want. If you spend 5 seconds, you get a decent panel. If you spend 10 minutes, you can push the limits and get pro results. Built-in Post-Processing: The editor’s features include liquify, upscale, remove background, and outpainting to extend an image. This allows artists to remove, add, or modify parts of an image on a pixel level without drawing by hand. We combine this with segmentation models like Segment Anything (https://github.com/facebookresearch/segment-anything) to support intelligently selecting and editing a part of an image. Google-docs like collaboration: The Studio runs in the browser and supports comments and collaboration. LLM Powered Copy Editor: Comics need text. An AI agent proofreads speech bubbles, fixes lettering and identifies grammar mistakes. Read our comics: https://shortbreadapp.com/ (free to download + read, iOS + Android) All of the above are built by a team of 3 engineers including myself. I will be around to answer any questions in this thread!
62 points · Open discussion
chrash·Apr 2, 2024
a big problem in the space is that products that look very similar will be clustered in the same section. large models are very good at generalizing, so they may be more attuned to "this is a Christmas thing", but they won't know that it should be classified as the same UPC as the thing that was in that spot yesterday without you specifically telling it to. how would it know it's not a misplaced product or a random piece of trash? (you won't believe the things you find on store shelves once you start looking) you can definitely speed up your annotation time with something like SAM[1], but it will never know without training or context that it's the same product but Christmas (ie it resolves to the same UPC). [1]: https://github.com/facebookresearch/segment-anything
In Amazon ditches 'just walk out' checkouts at its grocery stores
lelag·Mar 28, 2024
Some exciting projects from the last months: - 3d scene reconstruction from a few images: https://dust3r.europe.naverlabs.com/ - gaussian avatars: https://shenhanqian.github.io/gaussian-avatars - relightable gaussian codec: https://shunsukesaito.github.io/rgca/ - track anything: https://co-tracker.github.io/ https://omnimotion.github.io/ - segment anything: https://github.com/facebookresearch/segment-anything - good human pose estimate models: (Yolov8, Google's mediapipe models) - realistic TTS: https://huggingface.co/coqui/XTTS-v2, bark TTS (hit or miss) - open great STT (mostly whisper based) - machine translation (ex: seamlessm4t from meta) It's crazy to see how much is coming out of Meta's R&D alone.
In Ask HN: What things are happening in ML that we can't hear over the din of LLMs?
Stephen_Oladele·Sep 29, 2023
Webinar from last week on how to fine-tune VFMs, specifically Meta's Segment Anything Model (SAM). What you'll need to follow along the fine-tuning walkthrough: Images, ground-truth masks, and optionally, prompts from the Stamp Verification (StaVer) Dataset on Kaggle (https://www.kaggle.com/datasets/rtatman/stamp-verification-s...) Download the model weights for SAM the official GitHub repo (https://github.com/facebookresearch/segment-anything) Good understanding of the model architecture Segment Anything paper (https://ai.meta.com/research/publications/segment-anything/) GPU infra the NVIDIA A100 should do for this fine-tuning. Data curation and model evaluation tool Encord Active (https://github.com/encord-team/encord-active) Colab walkthrough for fine-tuning: https://colab.research.google.com/github/encord-team/encord-... I'd love
Read the rest
to get your thoughts and feedback. Thank you.
In How to Fine-Tune Foundation Models to Auto-Label Training Data
tysam_and·Aug 17, 2023Recommendation phrase
Yeah, they are great and some of the reason (up the causal chain) for some of the work I've done! Seems really fun! <3 :)))) Facebook's Segment Anything Model I think has a lot of potentially really fun usecases. Plaintext description -> Network segmentation (https://github.com/facebookresearch/segment-anything/blob/ma...) Not sure if that's what you're looking for or not, but I love that impressing your kids is where your heart is. That kind of parenting makes me very, very, very, happy. :') <3
In The Mathematics of Training LLMs
forgingahead·May 24, 2023
Interesting to see if/how this is different (or maybe built upon) Segment Anything[0]. For folks in the know: I often see segmentation models on video frames producing patchy results (see the DinoV2 video of the running dog, the body gets black patches randomly, so the segmentation fails for certain frames). What methods are folks using to deal with this - standard fine-tuning, or is there a way to "force" the area to be cleanly segmented (ie, add a bounding box around the class to supplement the data)? And is it something that can be implemented in foundation models, or are we always going to have patchy zero-shot results like this on video files? [0]https://github.com/facebookresearch/segment-anything
In Meta Open-Sources Computer Vision Foundation Model DINOv2
polygamous_bat·Apr 6, 2023
> According to the article, the weights haven't been open sourced, so nobody can take this and build their own Photoshop plugin. The article seems to be misleading, since I can just go to the github and download the weights right now: https://github.com/facebookresearch/segment-anything#model-c... However, for sake of fairness, competition, and reproducible science, I hope that if Adobe makes this a part of their commercial offering, they train their own so we can have two variants of the same model available to us.
In Meta Releases New AI-Based Photo Segmentation Tool to Everybody
fn-mote·Apr 6, 2023
Kind of off topic, but: I've never seen such crappy issues filed in a repo [1]. I don't read issues for major repositories, so perhaps this is standard? There are a ton of one line "issues", no clear example, test case, attempt to debug, not even a pull request for the one that points out a typo in the README. Gross. It seems like none of these issues will never be read because they are going to drown in garbage. [1] https://github.com/facebookresearch/segment-anything/issues
In Segment Anything Model (SAM) can "cut out" any object in an image

Showing the 15 most recent of 24 sources. Enable JavaScript to search and browse every indexed mention.

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.