CACardenB·Sep 26, 2024
Here’s some code: https://github.com/mlfoundations/open_clip?tab=readme-ov-fil...
In Xkcd 1425 (Tasks) turns ten years old todaymlfoundations
open_clip
Python2021–2024
mlfoundations / open_clip
open_clip
An open source implementation of CLIP.
11Distinct people
13Mentions
0Explicit recommenders
14.3KGitHub stars
What to know before exploring
What it is
An open source implementation of CLIP.
GitHub
Where it is used
No documented product use was verified in the last source check.
What people are saying
No recommendation phrase was found in the indexed comments.
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 8–Nov 15 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/15/2026, 4:00:59 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 year13 dated mentions
Observed mentions: 2021-07-31 19:58:51 UTC to 2024-09-26 06:43:05 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| 2021 | 2021-01-01 00:00:00 UTC | 2022-01-01 00:00:00 UTC | 2 | 1 | 1 |
| 2022 | 2022-01-01 00:00:00 UTC | 2023-01-01 00:00:00 UTC | 1 | 0 | 1 |
| 2023 | 2023-01-01 00:00:00 UTC | 2024-01-01 00:00:00 UTC | 4 | 0 | 4 |
| 2024 | 2024-01-01 00:00:00 UTC | 2025-01-01 00:00:00 UTC | 6 | 2 | 4 |
What Hacker News says
6 sourcesOpen_clip: An open source implementation of CLIP
3 points · Open discussionBeginner's Guide to Fine-Tuning Clip Models
2 points · Open discussionThe part of CLIP[1] that you need to know to understand this is that it embeds text and images into the same space. ie: the word "dog" is close to images of dogs. Normally this space is a high dimensional real space. Think 512-dimensional or 512 floating point numbers. When you want to measure "closeness" between vectors in this space cosine similarity[2] is a natural choice.
Why would you want to quantize values? Well, instead of using a 32-bit float for each dimension, what if you could get away with 1-bit? You would save you 31x the space. Often you'll want to embed millions or billions of pieces of text or images, so the savings represent a huge speed & cost savings and if accuracy isn't impacted too much then it could be worth it.
If you naively clip the floats of an existing model, it severely impacts accuracy. However, if you train
Read the rest
a model from scratch that produces binary outputs, then it appears to perform better.
There is one twist. Deep learning models rely on gradient descent to train and binary output doesn't produce useful gradients. We use cosine similarity on floating point vectors and hamming distance on bit vectors. Is there a function that behaves like hamming distance but is nicely differentiable? We can then use this function during training and then vanilla hamming distance during inference. It seems like they've done that.
I'd suggest playing around with OpenCLIP[3]. My background is in data science but all my CLIP knowledge comes from doing a side project over the course of a couple weekends.
1. https://huggingface.co/docs/transformers/model_doc/clip
2. https://en.wikipedia.org/wiki/Cosine_similarity
3. https://github.com/mlfoundations/open_clip
I have successfully used OpenCLIP models for embedding and similar-image search. The smallest model listed on that UForm page is 79 million parameters, so I presume that you can use other models of similar size. There are a few OpenCLIP models with 80 million or fewer parameters listed here:
https://github.com/mlfoundations/open_clip/blob/main/docs/mo...
When embeddings are quantized to int8 they still work very well for similarity (no differences in top 10 search on my test set). I haven't tried quantizing the models themselves.
In CatLIP: Clip Vision Accuracy with 2.7x Faster Pre-Training on Web-Scale DataIt is a misconception that Adobe's models have not been trained on copyrighted work. Nobody should be repeating their marketing claims.
Adobe has not shown how they train the text encoders in Firefly, or what images were used for the text-based conditioning (i.e. "text to image") part of their image generation model. They are almost certainly using CLIP or T5, which are trained on LAION2b, an image dataset with the very problems they are trying to address, C4 (a text dataset similarly encumbered) and similar.
I welcome anyone who works at Adobe to simply answer this question of how they trained the text encoders for text conditioning and put it to rest. There is absolutely nothing sensitive about the issue, unless it exposes them in a lie.
So no chance. I think it's a big fat lie. They'd have to have made some other scientific breakthroug
Read the rest
h, which they didn't.
Using information from https://openai.com/research/clip and https://github.com/mlfoundations/open_clip, it's possible to investigate the likelihood that using just their stock image dataset, can they make a working text encoder?
It's certainly not impossible, but it's impracticable. On 248m images (roughly the size of Adobe Stock), CLIP gets 37% on ImageNet, and on the 2000m from LAION, it performs 71-80%. And even with 2000m images, CLIP is substantially worse performing than the approach that Imagen uses for "text comprehension," which relies on essentially many billions more images and text tokens.