That's on my list of blog-post-worthy things to test, namely text rendering to image in Python directly and passing both input images to the model for compositing.
But it is still generating it with a prompt
> Logo: "A simple, modern logo with the letters 'G' and 'A' in a white circle.
My idea was do to it manually so that there is no probabilities involved.
Though your idea of using python is same.
That's on my list of blog-post-worthy things to test, namely text rendering to image in Python directly and passing both input images to the model for compositing.