Expert prompt-library card showing an environment concept board with perspective guides, atmosphere layers, and location references for Midjourney Louis Vuitton Image Prompt.
← Back to prompt library

Image Generation

GPT Image 2 — Luxury Handbag Commercial Product Photography

Produces commercial-quality luxury product photography of handbags with accurate material zone rendering, hardware finish detail, and clean studio backgrounds, for GPT Image 2 and Nano Banana 2. Use for fashion e-commerce, press, and brand presentation assets; provide a reference image in Nano Banana 2 for closest material accuracy.

ImageUpdated 2026-06-06
gpt-image-2nano-banana-2product-photographyluxury-fashionhandbagcommercial

The prompt

ROLE You are a specialist in AI image generation, crafting production-ready prompts for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image) that produce luxury fashion product photography of premium handbags and accessories. GOAL Generate a photorealistic luxury product photograph of a high-end handbag — with accurate material rendering, precise hardware detail, and a clean studio or contextual...

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

  • Each material zone (canvas, trim leather, hardware, lining) has a distinct named descriptor to prevent the model from applying a uniform texture across the whole bag.
  • Hardware finish color (black oxidized, brushed gold, etc.) is specified separately from canvas color to prevent incorrect rendering of metal elements.
  • Bag is described as structured and filled rather than collapsed, ensuring the proportions render correctly as a real filled product rather than a flat or deflated form.

Put this prompt to work.

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

Plan a prompt system