Can I use AI product photos in my online shop?

Not as a substitute for photographing the actual product — the model will alter details, which misrepresents what the buyer receives and creates a consumer-protection problem. They are useful for lifestyle backgrounds and lighting references.

How do I describe lighting in an image prompt?

Use photographic vocabulary: "single softbox from camera left", "golden hour", "overcast diffuse". The training data is labelled with those terms, whereas "nice lighting" steers almost nothing.

Which AI model is best for creating product photography with AI?

All of them handle this; what changes is the packaging. This page shows the same prompt written for image models. Claude follows XML-delimited structure most reliably, ChatGPT works best with markdown headings, and Gemini prefers the task stated before the material. The content of the prompt is identical in each.

Can I change this prompt for my own situation?

Yes, and you should. Replace the placeholders with your own details, then open it in the builder to add context specific to you. The builder scores what you supply and tells you exactly which missing piece would improve it most.

Why does this prompt include rules I did not ask for?

Because image tasks carry requirements that experienced practitioners apply automatically and rarely write down. The compiler adds them so the output does not fail on something obvious. Every added rule is listed on the how it works page.

AI prompt for creating product photography with AI

This is a ready-made AI prompt for creating product photography with AI, written for image models and free to copy. Generated product shots are unusable commercially if the product is not exactly your product — the model will subtly redesign it. They work for mood, lighting and composition references rather than final imagery. The prompt below handles that: it is compiled as a image task, so it carries the structure and the constraints that kind of work needs.

The prompt

Written for image models. Compiled as a image task — describing a visual result for an image generation model.

product photograph of {{product}}, on {{surface}}, {{background}}, shallow depth of field, sharp focus on the product, {{lighting}}, {{lens}}, commercial product photography, high detail, sharp focus --ar 4:5

Negative prompt: text, watermark, logo, hands, oversaturated, plastic sheen

Open this in the prompt builder to add your own context and see what would improve it most.

What makes creating product photography with AI hard to prompt for

Generated product shots are unusable commercially if the product is not exactly your product — the model will subtly redesign it. They work for mood, lighting and composition references rather than final imagery.

Why this prompt works

The task is stated before the material: For this kind of task the instruction is more useful up front, so the model knows what it is looking for as it reads. It is repeated at the end, because the last thing in the context carries the most weight.
Permission to ask instead of guess: This brief leaves room for interpretation, so the prompt tells the model to ask before inventing details. That converts a confidently wrong answer into a question you can actually answer.

What to replace

Placeholder	What to put there
{{product}}	Your product.
{{surface}}	Your surface.
{{background}}	Your background.
{{lighting}}	Your lighting.
{{lens}}	Your lens.

Check the output before you use it

Compare against the real product. Any redesigned detail rules it out for commercial use.
Check reflections and shadows are physically consistent with the stated light source.
Confirm no text or branding was hallucinated onto the packaging.

Common questions

Can I use AI product photos in my online shop?: Not as a substitute for photographing the actual product — the model will alter details, which misrepresents what the buyer receives and creates a consumer-protection problem. They are useful for lifestyle backgrounds and lighting references.
How do I describe lighting in an image prompt?: Use photographic vocabulary: "single softbox from camera left", "golden hour", "overcast diffuse". The training data is labelled with those terms, whereas "nice lighting" steers almost nothing.
Which AI model is best for creating product photography with AI?: All of them handle this; what changes is the packaging. This page shows the same prompt written for image models. Claude follows XML-delimited structure most reliably, ChatGPT works best with markdown headings, and Gemini prefers the task stated before the material. The content of the prompt is identical in each.
Can I change this prompt for my own situation?: Yes, and you should. Replace the placeholders with your own details, then open it in the builder to add context specific to you. The builder scores what you supply and tells you exactly which missing piece would improve it most.
Why does this prompt include rules I did not ask for?: Because image tasks carry requirements that experienced practitioners apply automatically and rarely write down. The compiler adds them so the output does not fail on something obvious. Every added rule is listed on the how it works page.

Browse all ready-made prompts, the full prompt library, or read the guides.