# Ideogram — Ideogram 4.0 Technical Details: Open model at the forefront of design

- Company: Ideogram
- Announced: 2026-06-03
- Category: open-weight-release
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://ideogram.ai/blog/ideogram-4.0
- Record: https://forck.live/items/15464-ideogram-4-0-technical-details-open-model-at-the-forefront-of-design
- Subject: Ideogram image models
- Open weights: yes
- Models affected: Ideogram 4.0

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.

## Evidence

Verbatim from https://ideogram.ai/blog/ideogram-4.0:

> Ideogram 4.0 is a 9.3B parameter open-weight text-to-image model. Recent open-weight releases have converged on a single self-attention sequence over text and image tokens [1] [2] [3] , and Ideogram 4.0 follows the same pattern: text and image tokens share the same projections at every layer of a 34-layer DiT.

---

Record: https://forck.live/items/15464-ideogram-4-0-technical-details-open-model-at-the-forefront-of-design
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md