open_clip
CLIP
Our great sponsors
open_clip | CLIP | |
---|---|---|
27 | 103 | |
8,391 | 22,051 | |
7.5% | 5.6% | |
8.4 | 1.2 | |
12 days ago | 11 days ago | |
Jupyter Notebook | Jupyter Notebook | |
GNU General Public License v3.0 or later | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
open_clip
-
A History of CLIP Model Training Data Advances
While OpenAI’s CLIP model has garnered a lot of attention, it is far from the only game in town—and far from the best! On the OpenCLIP leaderboard, for instance, the largest and most capable CLIP model from OpenAI ranks just 41st(!) in its average zero-shot accuracy across 38 datasets.
-
How to Build a Semantic Search Engine for Emojis
Whenever I’m working on semantic search applications that connect images and text, I start with a family of models known as contrastive language image pre-training (CLIP). These models are trained on image-text pairs to generate similar vector representations or embeddings for images and their captions, and dissimilar vectors when images are paired with other text strings. There are multiple CLIP-style models, including OpenCLIP and MetaCLIP, but for simplicity we’ll focus on the original CLIP model from OpenAI. No model is perfect, and at a fundamental level there is no right way to compare images and text, but CLIP certainly provides a good starting point.
-
Database of 16,000 Artists Used to Train Midjourney AI Goes Viral
It 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 breakthrough, 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.
-
MetaCLIP – Meta AI Research
https://github.com/mlfoundations/open_clip/blob/main/docs/op...
-
COMFYUI SDXL WORKFLOW INBOUND! Q&A NOW OPEN! (WIP EARLY ACCESS WORKFLOW INCLUDED!)
in the modal card it says: pretrained text encoders (OpenCLIP-ViT/G and CLIP-ViT/L).
-
Is Nicholas Renotte a good guide for a person who knows nothing about ML?
also, if you describe your task a bit more, we might be able to direct you to a fairly out-of-the-box solution, e.g. you might be able to use one of the pretrained models supported by https://github.com/mlfoundations/open_clip without any additional training
-
Generate Image from Vector Embedding
It says on the Stable Diffusion Github repo that it uses the “OpenCLIP-ViT/H” https://github.com/mlfoundations/open_clip model as a text encoder, and from my prior experience with CLIP, I have found that it is very easy to generate image and text embeddings (because CLIP is a multimodal model).
-
What's up in the Python community? – April 2023
https://replicate.com/pharmapsychotic/clip-interrogator
using:
cfg.apply_low_vram_defaults()
interrogate_fast()
I tried lighter models like vit32/laion400 and others etc all are very very slow to load or use (model list: https://github.com/mlfoundations/open_clip)
I'm desperately looking for something more modest and light.
-
Low accuracy on my CNN model.
A library that is very useful for this kind of application is timm. You may also find the feature representation provided by a CLIP model particularly powerful.
- Looking for OpenAI CLIP alternative
CLIP
-
How to Cluster Images
We will also need two more libraries: OpenAI’s CLIP GitHub repo, enabling us to generate image features with the CLIP model, and the umap-learn library, which will let us apply a dimensionality reduction technique called Uniform Manifold Approximation and Projection (UMAP) to those features to visualize them in 2D:
-
Show HN: Memories, FOSS Google Photos alternative built for high performance
Biggest missing feature for all these self hosted photo hosting is the lack of a real search. Being able to search for things like "beach at night" is a time saver instead of browsing through hundreds or thousands of photos. There are trained neural networks out there like https://github.com/openai/CLIP which are quite good.
-
Zero-Shot Prediction Plugin for FiftyOne
In computer vision, this is known as zero-shot learning, or zero-shot prediction, because the goal is to generate predictions without explicitly being given any example predictions to learn from. With the advent of high quality multimodal models like CLIP and foundation models like Segment Anything, it is now possible to generate remarkably good zero-shot predictions for a variety of computer vision tasks, including:
-
A History of CLIP Model Training Data Advances
(Github Repo | Most Popular Model | Paper | Project Page)
-
NLP Algorithms for Clustering AI Content Search Keywords
the first thing that comes to mind is CLIP: https://github.com/openai/CLIP
-
How to Build a Semantic Search Engine for Emojis
Whenever I’m working on semantic search applications that connect images and text, I start with a family of models known as contrastive language image pre-training (CLIP). These models are trained on image-text pairs to generate similar vector representations or embeddings for images and their captions, and dissimilar vectors when images are paired with other text strings. There are multiple CLIP-style models, including OpenCLIP and MetaCLIP, but for simplicity we’ll focus on the original CLIP model from OpenAI. No model is perfect, and at a fundamental level there is no right way to compare images and text, but CLIP certainly provides a good starting point.
-
COMFYUI SDXL WORKFLOW INBOUND! Q&A NOW OPEN! (WIP EARLY ACCESS WORKFLOW INCLUDED!)
in the modal card it says: pretrained text encoders (OpenCLIP-ViT/G and CLIP-ViT/L).
-
Stability Matrix v1.1.0 - Portable mode, Automatic updates, Revamped console, and more
Command: "C:\StabilityMatrix\Packages\stable-diffusion-webui\venv\Scripts\python.exe" -m pip install https://github.com/openai/CLIP/archive/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1.zip --prefer-binary
-
[D] LLM or model that does image -> prompt?
CLIP might work for your needs.
-
Where can this be used? I have seen some tutorials to run deepfloyd on Google colab. Any way it can be done on local?
pip install deepfloyd_if==1.0.2rc0 pip install xformers==0.0.16 pip install git+https://github.com/openai/CLIP.git --no-deps pip install huggingface_hub --upgrade
What are some alternatives?
DALLE-pytorch - Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch
sentence-transformers - Multilingual Sentence & Image Embeddings with BERT
taming-transformers - Taming Transformers for High-Resolution Image Synthesis
latent-diffusion - High-Resolution Image Synthesis with Latent Diffusion Models
Dreambooth-Stable-Diffusion - Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion
disco-diffusion
bitsandbytes - Accessible large language models via k-bit quantization for PyTorch.
DALLE2-pytorch - Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
clip-retrieval - Easily compute clip embeddings and build a clip retrieval system with them
BLIP - PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
stablediffusion - High-Resolution Image Synthesis with Latent Diffusion Models
txtai - 💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows