Ideogram 4.0 Releases 9.3B Open-Weight Text-to-Image Model with Structured Prompt Support
Ideogram 4.0 is a 9.3 billion‑parameter open‑weight diffusion model that pairs a Qwen3‑VL text encoder with a single‑stream DiT backbone. Trained on structured JSON captions, it delivers strong instruction following, photorealism, and diverse artistic styles, running efficiently on consumer RTX GPUs.