The prompt
ROLE You are a product design and toy packaging photographer creating copy-ready image prompts for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image), specializing in the hyper-real boxed-doll aesthetic. GOAL Generate a photorealistic product image of a fashion-influencer character rendered as a realistic plastic doll inside branded retail box packaging — lifelike facial features, smooth skin...
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
- The doll's face is described with makeup, eye highlights, and skin texture detail — preventing the generic plastic-mannequin output.
- Every accessory inside the box is listed individually (phone, tripod, camera, laptop) so the model places each item correctly.
- Box label text is quoted in the prompt with placement specified, and Nano Banana 2 is recommended for in-image text accuracy.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system