Image generation and editing with OpenAI's GPT Image 2, optimized for embedded text, logos, and layout precision.

• Excels at rendering embedded text, multilingual typography, and brand-safe imagery; use when directive precision and canvas composition matter more than stylization
• Two endpoints: text-to-image and edit (with up to 10 reference images for guidance); three fixed output sizes (1:1, 2:3 portrait, 3:2 landscape)
• Invoked via RunComfy CLI (runcomfy run openai/gpt-image-2/<endpoint>); requires RunComfy account and token authentication
• Prompting best practices include explicit subject + setting + mood, quoted embedded text kept short, compositional cues, and single-attribute iteration for refinement