From the source
Ideogram released Ideogram 4.0, a 9.3B parameter open-weight text-to-image model.
- The model uses a 34-layer Diffusion Transformer with a Qwen3-VL-8B-Instruct text encoder and is trained exclusively on structured JSON captions with per-element styling, optional bounding boxes, and color palettes.
- The reference inference pipeline validates prompts against the JSON schema before generation.




