MultimodalOpenAI

OpenAI launches native image generation in GPT-4o

Made by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made

Native image generation in GPT-4o

Why it matters

The official description runs tokens → transformer → diffusion → pixels — not purely autoregressive (AR), but a hybrid of AR token generation and a diffusion decoder

Source — Primary sources first; secondary reports are labelled “Press”

Officialopenai.comhttps://openai.com/index/introducing-4o-image-generation/

Added in Week 35, 2026 · See that week

On the map — ⑦ Multimodal line

  1. Previous stopGoogle DeepMind
  2. This recordOpenAI launches native image generation in GPT-4o
  3. Next stopDeepSeek-OCR
See it on the map

Same week

xAI acquires X Corp in an all-stock dealPressOn the Biology of a Large Language ModelOfficialOpenAI adopts MCP (Agents SDK)PressMCP releases spec 2025-03-26Official

Nearby on the same axis

Google DeepMind introduces Gemini Robotics / Robotics-EROfficialVeo 3OfficialGenie 3OfficialGemini 2.5 Flash Image (nano-banana)Official