It's a surprisingly difficult task with quite a bit of research history.

We looked at different solutions extensively (https://medium.com/towards-data-science/editing-text-in-imag...) and ended up building a tool to solve the problem: https://www.producthunt.com/posts/textify-2

Eventually models will get to the point where they can do this well natively but for now the best we can do is a post-processing step.

Thanks for the feedback! We included the login just so we have a way of helping people track their progress. What do you primarily see as the downsides to providing that option?

Time estimates and additional languages are certainly something we can look into. Which ones would you want supported?

The login is great but I was referring to another option that just uses email rather than Facebook or Google.

I've used python, matlab, and javascript. Python certainly makes the most sense for machine learning but might be nice to also be able to learn a new language at the same time if there's another language that makes sense for machine learning.