Multimodality · 2025
Introducing 4o Image Generation
Replaced DALL·E in ChatGPT with image output native to the LLM via an autoregressive approach, delivering reliable in-image text and conversational multi-turn editing and mainstreaming native image generation.
Editorial record
Plain-language summary
Replaced DALL·E in ChatGPT with image output native to the LLM via an autoregressive approach, delivering reliable in-image text and conversational multi-turn editing and mainstreaming native image generation.
Knowledge graph
Relationships
Descendants
Depends onEvidence: Strongly supported
Attention Is All You Need
Builds on the multimodal lineage in the archive
freshness sweep 2026
Source record
Provenance
- Record ID
- P-653
- Record created
- 2026-07-13
- Last reviewed
- 2026-07-14
- Record version
- 2
Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.