Bumblebee is out: GPT2, Stable Diffusion, and More in Elixir (and LiveBook)

@wojtekmach thank you so much. As I suspected, totally a user error and a pretty silly one! Starts up perfectly fine now. Sorry for the noise. Very excited by what this represents for several of my libraries!

Example

iex> Image.open!("./test/support/images/lamborghini-forsennato-concept.jpg") 
...> |> Image.Classification.classify()
%{predictions: [%{label: "sports car, sport car", score: 0.9962735176086426}]}
9 Likes

BTW, just recently I found the following article that combines Phoenix, Axon and Elasticsearch.

It focuses on semantic search on text and not on images. I have not reproduced its content yet. Just note that it also involves some Python.

1 Like

@bdarla I’m going to update that post soon to be 100% Elixir with Axon, Bumblebee, and a library that completely eliminates the need for an additional service in Elasticsearch :slight_smile:

15 Likes

2 posts were split to a new topic: How to use Bumblebee to train a dataset for product recognition in our ecommerce setup?

:sweat_smile:

9 Likes

I would have to check but I dont think we sell any nipples :thinking:

1 Like

2 posts were split to a new topic: Server/deployment considerations for Bumblebee?

Amazing work!

To check if GPU is supported, visit GitHub - elixir-nx/xla: Pre-compiled XLA extension and see usage of XLA_TARGET. To load the correct version, set the environment variable XLA_TARGET to the desired version (I used XLA_TARGET=cuda118 for an RTX 3090 card). Make sure that the version you choose is installed on your system (e.g. CUDA).

3 Likes

FYI, the update post for this will be following this one: https://dockyard.com/blog/2023/01/04/search-and-clustering-with-exfaiss

5 Likes

Hi guys,

I am following along the Livebook demos by release notes and I reached to the ML examples. Got excited to test the Stable Diffusion model and generate some silly pictures.

The model just downloads 2GBs of data and then I get an error from Bumblebee.

Maybe I can provide an image?

The error ** (ErlangError) Erlang error: :edquot suggests that the disk quota was reached.

Maybe there’s no disk space available anymore to download the model’s weights?

1 Like

I think that is probably it. Thank you very much!