Show HN: depot.ai – easily embed ML / AI models in your Dockerfile

7 points

3 years ago

Hey HN! We're excited to launch https://depot.ai today - depot.ai is an open-source Docker registry that makes it easy to embed public models from Hugging Face in your Docker images using a `COPY`:

  # Copy all files from the model repo to the current WORKDIR 
  COPY --link --from=depot.ai/runwayml/stable-diffusion-v1-5 / . 
  
  # COPY just one file from the model repo to the current WORKDIR 
  COPY --link --from=depot.ai/runwayml/stable-diffusion-v1-5 /v1-5-pruned.ckpt .

To optimize build speed, cache hits, and registry storage, we're building each image reproducibly and indexing the contents with eStargz[0]. The image is stored on Cloudflare R2, and served via a Cloudflare Worker. Everything is open source[1]!

Compared to alternatives like `git lfs clone` or downloading your model at runtime, embedding it with `COPY` produces layers that are cache-stable, with identical hash digests across rebuilds. This means they can be fully cached, even if your base image or source code changes.

And for Docker builders that enable eStargz, copying single files from the image will download only the requested files. eStargz can be enabled in a variety of image builders[2], and we’ve enabled it by default on Depot[3].

Here’s an announcement post with more details: https://depot.dev/blog/depot-ai.

We’d love to hear any feedback you may have!

[0] https://github.com/containerd/stargz-snapshotter/blob/main/docs/estargz.md

[1] https://github.com/depot/depot.ai

[2] https://github.com/containerd/stargz-snapshotter/blob/main/docs/integration.md#image-builders

[3] https://depot.dev

1 comment