Ideogram releases Ideogram 4.0 open model

// 2h agoMODEL RELEASE

Ideogram releases Ideogram 4.0 open model

Ideogram 4.0 is a 9.3B parameter open-weight diffusion transformer model featuring bounding-box layout control, native transparency, and multilingual text rendering at 2K resolution. Using a structured JSON prompting system, it allows developers to direct image generation with specific coordinates and color codes to automate design workflows.

// ANALYSIS

This release is a major win for open-source AI design, offering granular spatial control that challenges closed-source leaders.

* Bounding-box layout control and JSON prompting enable developers to build highly structured design-ready image applications.

* Native transparency support and precise multilingual text rendering solve core design friction points, eliminating manual background removal and text errors.

* The open-weight nature (9.3B parameters) allows for local execution and fine-tuning, driving enterprise adoption.

// TAGS

design-toolsopen-sourcesocial-mediagithubimage-gendiffusion-model

DISCOVERED

2h ago

2026-06-05

PUBLISHED

7h ago

2026-06-05

RELEVANCE

8/ 10

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE52m ago

Anthropic adds 'Dreams' to Managed Agents API

Anthropic launched "Dreams", an asynchronous memory consolidation feature for the Claude Managed Agents API. The offline job prunes stale context and resolves contradictions, resulting in a cleaner and more performant long-term memory store.

MODEL1h ago

Gemma 4 12B Assistant accelerates decoding

The Gemma 4 12B IT Assistant checkpoint has caused developer confusion, as it is actually a speculative decoding drafter model rather than a standalone chatbot. When configured in tools like vLLM alongside the primary model, it accelerates inference via Multi-Token Prediction without degrading quality.

BENCHMARK1h ago

Google's Gemma 4 12B model faces criticism for slow local performance and poor multimodal generation on Apple Silicon.

A developer tested Google's Gemma 4 12B model on a MacBook Pro M5 Max with 128GB of unified memory, finding its performance disappointing for a model of its size. Achieving only 44 tokens per second, the developer noted that the model's generation quality was subpar—specifically criticizing a produced lava lamp image—and recommended developers stick with Qwen 3.6 27B or 35B instead.