Pose the question the demos never explain: how does typing a sentence produce a detailed image? The answer in US20230377226A1 (published November 23, 2023; inventors include the team behind Google's image-generation research) is: in stages. One model turns text into a small, low-resolution image; subsequent models upscale and sharpen it.
Here's why coarse-to-fine is the smart move. Generating a full high-resolution image directly is enormously hard, too many pixels to get right at once. Breaking it into stages lets the first model nail the composition cheaply (where's the dog, what's the background) and later models add detail without rethinking the whole scene. The CPC tags span G06T (image processing), G06F 40/40 (NLP for the prompt), and G06N 3/08 (neural learning).
Under the hood, this is a relay race. Each generative network hands off to the next, and each is specialized: the first for layout-from-text, the later ones for super-resolution. Crucially, the text prompt can guide multiple stages, so the refinement stays faithful to what you asked for rather than drifting.
Why this matters for the sector: staged generation is a big part of why text-to-image went from blurry curiosities to photorealistic output in a couple of years. It's also a compute story, spending most of the expensive work at low resolution and reserving the rest for upscaling is far cheaper than brute-forcing full resolution end to end.
House caveat: a publication describes a method, not the specific quality of any product, and image-generation quality depends on training data and scale the patent doesn't fix. But the filing dates the architecture precisely, by late 2023, coarse-to-fine generation via a sequence of networks was core, named, claimed Google IP.