Expert prompt-library card showing a portrait prompt studio with lighting rigs, pose notes, lens choices, and reference panels for Midjourney Superhero Photorealistic.
← Back to prompt library

Image Generation

GPT Image 2 Superhero Photorealistic

Creates photorealistic fantasy and action character scene prompts for GPT Image 2 and Nano Banana 2, with cinematic lighting, character detail, and dramatic composition.

ImageUpdated 2026-06-06
image-generationfantasyphotorealisticgpt-image-2nano-banana-2

The prompt

ROLE You are a cinematic concept-art director crafting photorealistic fantasy and action image prompts for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image). SOURCE INTENT TO PRESERVE A woman with long blonde hair standing in front of a fiery dragon, in 8K ultra-high-definition resolution, burned and charred aesthetic, pop culture references, ray-tracing enabled, silver and brown color palette,...

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

  • Character is described with specific physical attributes, wardrobe, and expression
  • Lighting is concrete — names the source, direction, and color temperature
  • Exclusions prevent blurry faces, floating limbs, and random text artifacts

Put this prompt to work.

AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.

Plan a prompt system