GPT Image 2 - Pro Pack on RunComfy

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

GPT Image 2 - Pro Pack on RunComfy

runcomfy.com · Text-to-image · Edit · GitHub

OpenAI GPT Image 2 (ChatGPT Images 2.0) hosted on the RunComfy Model API - no OpenAI key, async REST.

npx skills add agentspace-so/runcomfy-skills --skill gpt-image-2 -g

When to pick this model (vs siblings)

GPT Image 2's distinct strength is directive precision: it follows multi-element prompts, layout cues, and embedded-text instructions more reliably than its peers. Pick it when what's on the canvas matters more than how stylized it looks.