Reve V2.1 is Reve's flagship image model, built around two things most generators struggle with: following a long prompt exactly, and writing text that is actually readable. That makes it the one to reach for when the words on the artwork carry meaning, such as a tavern sign, a spell scroll heading, or a labelled map.
Quoted text comes out legible and correctly spelled far more often than with general-purpose models. Seventeen aspect ratios cover everything from 4:1 map banners to 1:4 vertical standards, and the same model edits an existing image from a plain-language instruction, so you can fix a detail without regenerating the whole piece.
Put the exact wording in quotes inside your prompt, for example a banner reading "House Valen". Quoted text is reproduced much more reliably than text you only describe.
Yes. Upload a reference image and describe the change in plain language. It routes to the edit model automatically, and the price is the same 33 gold as a fresh generation.
33 gold per image, flat. Text-to-image and editing cost the same, and the aspect ratio does not change the price.
Anything where the words on the artwork matter: tavern signs, spell scrolls, wanted posters, faction banners, labelled maps, and item cards.