← Back to articles
OpenAI's GPT-Image-2 handles complex image workflows including editing, one week after release
Hacker News · April 28, 2026
AI Summary
- •OpenAI released GPT-Image-2, a new image generation model that has been available for a week. The model can handle most image workflows and perform image editing.
- •Unlike earlier image generation models that struggled with rendering hands correctly, GPT-Image-2 can manage complex tasks and, like Google's comparable model, can reason and include accurate information in generated images.
- •A user created a lead image for a story using GPT-Image-2 instead of their usual manual Photoshop workflow with a template.
Related Articles
Large Language Models
Researchers release talkie, a 13B-parameter language model trained only on texts published before 1931, to study how AI interprets a world it has no knowledge of beyond that cutoff.
THE DECODER·Apr 28, 2026
Large Language Models
Anthropic reports service outages affecting Claude.ai, API, and Claude Code; issues resolved after 78 minutes
Hacker News·Apr 28, 2026
Large Language Models
Anthropic launches connectors that let Claude integrate directly with Creative Cloud, Blender, Ableton, and other creative software.
The Verge AI·Apr 28, 2026
Large Language Models
Amazon launches desktop AI agent Quick and expands Connect platform with four agentic AI services for enterprise software market
Yahoo Finance AI·Apr 28, 2026
Large Language Models
Oracle stock falls 15% in 2026 amid concerns over OpenAI's spending commitments following missed user and revenue targets
Yahoo Finance AI·Apr 28, 2026
Stay ahead with AI news
Get curated AI news from 200+ sources delivered daily to your inbox. Free to use.
Get Started Free