Blog Illustration Prompt Generator

Goal

Generate one ready-to-use English prompt for an image model to create a blog/article illustration.

Success Criteria

A good result:

• Returns one text prompt, not an image.
• Keeps the prompt around 200-400 words unless the user asks for a different format.
• Names the intended visual outcome, layout, metaphors, labels, style constraints, and technical specs.
• Uses concrete visual anchors from the user's content without inventing product facts, metrics, customers, roadmap claims, or architecture details.
• Stops after the prompt unless the user asks for explanation or direct image generation.

Core Constraints

The prompt itself must be written in English, regardless of the conversation language. Use Chinese labels only when the user explicitly requests Chinese text inside the image.