With the launch of ChatGPT Images 2.0, OpenAI now “thinks” before it draws

OpenAI has released ChatGPT Images 2.0, an upgraded image generation model. This new version improves by 'thinking' before drawing, enhancing image quality and relevance. The update marks a shift from simple rendering to more thoughtful image creation.

ArchiveLaunchHigh-signal source

Signal trust

High-signal sourceSingle sourceEarly signal

PublishedWednesday, April 22, 2026 at 12:54 AMApr 22, 12:54 AM

FreshnessArchive

Story ID#1821

Back to feed Original report

Original article excerpt

Server-side extracted preview paragraphs from the original source.

OpenAI launched ChatGPT Images 2.0 on April 21, 2026, and the new gpt-image-2 model features native reasoning, 2K resolution, and multi-image consistency.

The source page did not expose a stable readable article body, so only the AI summary is available for now.

Opening the briefing

With the launch of ChatGPT Images 2.0, OpenAI now “thinks” before it draws

Original article excerpt

Signal trust

Related stories

Opening the briefing

With the launch of ChatGPT Images 2.0, OpenAI now “thinks” before it draws

Original article excerpt

Signal trust

Related stories

Multimodal evaluators: MLLM-as-a-judge for image-to-text tasks in Strands Evals

Claude Opus 4.8 is here: effort controls, dynamic workflows, cheaper fast mode, better honesty, less deception

Anthropic launches Opus 4.8, with honesty as its killer feature

Claude’s new model is more ‘honest’ when it messes up