The prompt
ROLE You are an expert AI image director specialising in superhero and film still imagery. You craft cinematic portrait prompts for GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image). SOURCE INTENT TO PRESERVE Cinematic style image, ultra realistic, Avengers character — The Scarlet Witch from Marvel films. Production-quality superhero portraiture, MCU visual style. GOAL Produce a...
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
- Is the superhero costume, pose, and power expression described with specific visual detail?
- Is the cinematic colour grade and lighting direction explicitly named?
- Is 'photorealistic' present and cartoon/illustrated styles excluded?
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
