meadowrun VS dalle-playground

If you’re anything like us, though, you’ll feel compelled to poke around the code and run the model yourself. We’ll do that in this article using Meadowrun, an open-source library that makes it easy to run Python code in the cloud. For ML models in particular, we just added a feature for requesting GPU machines in a recent release. We’ll also feed the images generated by DALL·E Mini into additional image processing models (GLID-3-xl and SwinIR) to improve the quality of our generated images. Along the way we’ll deal with the speedbumps that come up when running open-source ML models on EC2.

So it is more reasonable to cache the download locally for up to 4 hours. That saves us 5–10 seconds on every run.

Built on dalle-playground because it is simple and I like it.

[1] https://github.com/saharmor/dalle-playground

If you decide to abandon the idea of running locally and want to run in the cloud instead, https://github.com/saharmor/dalle-playground has a Google Colab notebook that's relatively easy to run (although Google Colab's free tier is relatively limited).

Next, we want the code in the https://github.com/hrichardlee/dalle-playground repo, and we want to construct a pip environment from the backend/requirements.txt file in that repo. We were almost able to use the saharmor/dalle-playground repo as-is, but we had to make one change to add the jax[cuda] package to the requirements.txt file. In case you haven’t seen jax before, jax is a machine-learning library from Google, roughly equivalent to Tensorflow or PyTorch. It combines Autograd for automatic differentiation and XLA (accelerated linear algebra) for JIT-compiling numpy-like code for Google’s TPUs or Nvidia’s CUDA API for GPUs. The CUDA support requires explicitly selecting the [cuda] option when we install the package.

Is their any way to run DALLE-2 inside of a docker container similarly to this DALLE-PLAYGROUND repo on github?

I know there are open source projects like dalle-playground. Would it literally be enough to host this app on an EC2 instance with the mini model?