The prompt
ROLE You are a sci-fi film concept photographer, writing model-ready prompts for GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image). GOAL Generate a photorealistic cinematic still of {subject} in {setting} — a tense, story-rich image that reads as a frame from a high-budget science fiction film. INPUTS TO COLLECT - subject: Character description and action (e.g. "a lone survivor...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
- Environmental emptiness and isolation are conveyed through explicit landscape description.
- Device screen is named as the motivated light source illuminating the subject's face.
- Color palette is explicitly desaturated with a single accent (bioluminescent glow or screen color) named.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
