natural-language-image-search VS CLIP

You have the option of deleting and posting again I think. Anyways good luck.

Wikimedia search seems to work better for most searches I tried, possibly because of the manual tags etc.

https://imagioo.com/?q=astronaut+with+american+flag

https://commons.wikimedia.org/wiki/Special:MediaSearch?type=...

You might want to include examples where your search is better or just a faq on how to use it.

Nice idea though. It does seem to come in handy when you don't have descriptions of images. Eg: https://github.com/haltakov/natural-language-image-search

You can give OpenAI's CLIP a shot: https://github.com/openai/CLIP. It's capable of doing zero-shot classification. Here is a neat example of CLIP usage: https://github.com/haltakov/natural-language-image-search.

Does this use the same codebase as https://github.com/haltakov/natural-language-image-search ? Or do you have a different approach?

CLIP Image Search

Yes, this is definitely possible. You can maybe try computing some kind of image distance between frames or some keyframe extraction.

Once you compute the features, the search is very efficient! I tried it for searching in the 2M photos dataset from Unsplash and it takes like 2-3 seconds: https://github.com/haltakov/natural-language-image-search

I plan to run my personal photos through it :)

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:

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.

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:

(Github Repo | Most Popular Model | Paper | Project Page)

the first thing that comes to mind is CLIP: https://github.com/openai/CLIP

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.

in the modal card it says: pretrained text encoders (OpenCLIP-ViT/G and CLIP-ViT/L).

Command: "C:\StabilityMatrix\Packages\stable-diffusion-webui\venv\Scripts\python.exe" -m pip install https://github.com/openai/CLIP/archive/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1.zip --prefer-binary

CLIP might work for your needs.

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