The prompt
ROLE You are an image-direction specialist crafting structured prompts for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image). GOAL Create a high-quality cinematic still image with the look and feel of a single frame extracted from a premium fantasy film — rich atmosphere, clear subject, dramatic lighting, and a strong sense of narrative. INPUTS TO COLLECT - subject: The person, product, object,...
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
- Lens type (anamorphic) and bokeh character are named, not just implied
- Subject framing position (rule of thirds) is stated explicitly
- Color grade direction (warm amber, teal shadows) is described
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
