ente VS CLIP

I religiously use Google contacts. It's the simplest way to keep people contacts up to date on Android.

I archive all important documents in specific folders by subject and date. This is backed up to back blaze with restic. https://restic.net/

I use https://ente.io for pictures. I convinced my wife to use it, and she agreed to auto share her photos so I don't nag her for copies. It had simple import from Facebook and Google.

I also keep extensive journals, which really helps to tie it all together. I can basically grep for hangouts, conversations, etc.

I also separate work journal from personal, and have essentially a journal for each project. https://jodavaho.io/tags/bullet-journal.html for how.

I religiously use Google calendar for all plans, you can easily search it for past events to get dates.

I also use monicahq for some notes about things I should remember about people but the habit never stuck.

> How does one get their data out of the cloud ente.io - and into a self hosted instance of the server? Is there any data loss during this process?

Just to jump in cause I was curious myself. I think your question is answered here:

"Command Line Utility for exporting data from Ente"

https://github.com/ente-io/ente/tree/main/cli

pip install -U huggingface_hub umap-learn git+https://github.com/openai/CLIP.git

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.