More specifically, Nano Banana is tuned for image editing: https://gemini.google/overview/image-generation

Yep, Google actually recommends using Imagen4 / Imagen4 Ultra for straight image generation. In spite of that, Flash 2.5 still scored shockingly high on my text-to-image comparisons though image fidelity is obviously not as good as the dedicated text to image models.

Came within striking distance of OpenAI gpt-image-1 at only one point less.

Is it a single model or is it a pipeline of models?

Single model, Gemini 2.5 Flash with native image output capability.

[misread]

They're referring to Case 1 Illustration to Figure, the anime figurine dressed in a maid outfit in the HN post.

I assume OP means the actual post.

The second example under "Case 1: Illustration to Figure" is a panty shot.

This was reported and has been removed recently (https://github.com/PicoTrex/Awesome-Nano-Banana-images/issue...), although the issue wasn't closed.

For anyone confused, the offending example got removed 10 minutes ago

https://github.com/PicoTrex/Awesome-Nano-Banana-images/tree/... if you want to see it.

I have no idea how people think they can interact with an art related product with this kind of puritanical sensibility.