Introducing MakeReal in jupyter-tldraw ✨ Now you can hand-draw a plot on a tldraw whiteboard and turn it into Matplotlib code directly in a notebook.

You can find the source code and installation instructions here

@tldraw @matplotlib I'm eager to learn about potential use cases. Based on the current demo how is this better than, say choosing the plot type from a dropdown list?

@tldraw @matplotlib Same here, I'm also very interested in use-case investigation! One advantage I can see in hand-drawn plots is that I can exactly describe what I want. E.g. this example would not be possible to find in an example gallery with this level of custom details.

@tldraw @matplotlib Have I ever told you that I really want a detexify type search of the gallery?

@tldraw @matplotlib Oh, absolutely! One could even think of an open source language model trained on the matplotlib gallery.

@tldraw @matplotlib I'm curious how this works! Is it powered by gpt-4-vision? 🙃

@tldraw @matplotlib Yep, the model is called `gpt-4-vision-preview` and here is how I sent the request Under the hood, I'm using traitlets with #anywidget to transport the image. That's very modular, so it would also be possible to connect other large language models.

@tldraw @matplotlib Who is doing that freehand drawing? I couldn't draw something that steady if my life depended on it.

@tldraw @matplotlib I'll plan a more paw friendly interface!🐕 😉

@tldraw @matplotlib Jaw-dropping!