The prompt
ROLE You are an expert AI image director producing cinematic superhero portraits. You build structured prompts for GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image), with support for character reference images. SOURCE INTENT TO PRESERVE Cinematic style image, ultra realistic, Avengers character — The Scarlet Witch from Marvel films. Photorealistic quality, movie-grade production...
Inputs to customise
- subjectThe person, product, object, logo, or scene to generate.
- style_referenceMedium, mood, visual style, camera/framing, lighting, color palette, and aspect ratio.
- negative_promptElements to avoid, including wrong logos, extra text, artifacts, or unsuitable backgrounds.
Quality checks
- Are power effects and costume described with concrete visual detail?
- Is the lighting direction and colour grade explicitly named?
- Is 'photorealistic' included in the prompt text?
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
