# AI Product Photo Generator

> Agent skill on puras — published by puras. AI product photography for any subject — a product, app, café, or service. It studies your uploaded photos, writes a scenario that fits the subject, and renders ONE cohesive, art-directed, social-ready photo with a deliberate concept, palette, and light.

- **Skill path:** `puras/product-ad-studio/social-photo`
- **Skillpack:** Product Ad Studio (`product-ad-studio`)
- **Skillpack ID:** `39903015-da3d-49a2-b549-9256ef164430`
- **Deployment version:** v58
- **Human page:** https://puras.co/skills/puras/product-ad-studio/social-photo
- **API base:** `https://api.puras.co`

## Description

AI product photography for any subject — a product, app, café, or service. It studies your uploaded photos, writes a scenario that fits the subject, and renders ONE cohesive, art-directed, social-ready photo with a deliberate concept, palette, and light.

## Try it free

AI Product Photo Generator has a free in-browser playground on its page (https://puras.co/skills/puras/product-ad-studio/social-photo) — load an example or bring your own inputs and run it with a Google sign-in. No credit card, no subscription; runs are usage-based after the free try.

## Input schema

```json
{
  "type": "object",
  "required": [
    "product_images"
  ],
  "properties": {
    "brief": {
      "type": "text",
      "maxLength": 2000,
      "description": "Optional. What it is, who it's for, the vibe. A URL works too."
    },
    "style": {
      "enum": [
        "auto",
        "premium",
        "minimal",
        "warm",
        "bold",
        "playful",
        "natural",
        "editorial"
      ],
      "type": "string",
      "description": "Visual tone for the set. `auto` picks the best fit for the subject."
    },
    "aspect_ratio": {
      "enum": [
        "9:16",
        "4:5",
        "1:1",
        "16:9"
      ],
      "type": "string",
      "default": "1:1",
      "description": "Output frame for the photo. Default 1:1."
    },
    "include_people": {
      "type": "boolean",
      "default": true,
      "description": "Allow shots with anonymous people (in-use, on-model, a café guest). On by default."
    },
    "product_images": {
      "type": "array",
      "items": {
        "type": "image"
      },
      "maxItems": 5,
      "minItems": 1,
      "description": "Photos of what you're promoting — a product packshot, an app screenshot or device mockup, your storefront/interior, a dish, anything. Clean, well-lit shots work best. Whatever it is, it stays true across the set.\n"
    }
  }
}
```

## Output schema

```json
{
  "type": "object",
  "properties": {
    "photo": {
      "type": "image",
      "description": "The finished social product photo."
    }
  }
}
```

## Examples

### Layered tropical iced drink

Just the product photo — no brief. The skill reads it as a food/drink subject, invents one golden-hour concept, and returns a single cohesive hero photo.

Inputs:

```json
{
  "style": "natural",
  "aspect_ratio": "1:1",
  "include_people": true,
  "product_images": [
    "https://uozfqcfhlhugotnevscg.supabase.co/storage/v1/object/public/puras-public-skills/product-ad-studio/tropical-product.webp"
  ]
}
```

Outputs:

```json
{
  "photo": "https://uozfqcfhlhugotnevscg.supabase.co/storage/v1/object/public/puras-public-skills/product-ad-studio/tropical-hero.webp"
}
```

### Deluxe hardcover book

Just the cover photo — no brief, style auto. The skill reads it as a physical product, sets one concept and returns a single finished photo.

Inputs:

```json
{
  "style": "auto",
  "aspect_ratio": "1:1",
  "include_people": true,
  "product_images": [
    "https://uozfqcfhlhugotnevscg.supabase.co/storage/v1/object/public/puras-public-skills/examples/product-ad-studio/product-social-creative-photos/25499ab2/product_images-0.png"
  ]
}
```

Outputs:

```json
{
  "photo": "https://uozfqcfhlhugotnevscg.supabase.co/storage/v1/object/public/puras-public-skills/examples/product-ad-studio/product-social-creative-photos/25499ab2/out-photos-0-output_url.webp"
}
```

## Use this skill

puras runs this skill on its own backend — you send inputs and get the result back. Three ways to call, fastest first:

### 1. MCP server — recommended for coding agents, no API key

Connect the puras MCP server; auth is OAuth in the browser on first call, so there is nothing to paste.

```bash
claude mcp add --transport http puras https://mcp.puras.co/mcp
```

Any MCP client works — point it at `https://mcp.puras.co/mcp` (HTTP transport). Then ask the agent to run `social-photo` from skillpack `puras/product-ad-studio` with your inputs.

### 2. CLI / Python SDK — `pip install puras`

```bash
pip install puras
puras login            # or set PURAS_API_KEY
puras run puras/product-ad-studio/social-photo -i key=value
```

From Python:

```python
import puras

client = puras.Client()   # PURAS_API_KEY from env
result = client.run("puras/product-ad-studio/social-photo", {"style":"natural","aspect_ratio":"1:1","include_people":true,"product_images":["https://uozfqcfhlhugotnevscg.supabase.co/storage/v1/object/public/puras-public-skills/product-ad-studio/tropical-product.webp"]})
```

### 3. HTTP API

`wait=true` blocks until the run reaches a terminal status and returns the result inline.

```bash
curl -X POST "https://api.puras.co/v1/jobs?skillpack=puras/product-ad-studio&wait=true" \
  -H "Authorization: Bearer $PURAS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"skill":"social-photo","inputs":{"style":"natural","aspect_ratio":"1:1","include_people":true,"product_images":["https://uozfqcfhlhugotnevscg.supabase.co/storage/v1/object/public/puras-public-skills/product-ad-studio/tropical-product.webp"]}}'
```

Mint an API key (for CLI / SDK / API) from https://puras.co/api-keys.

## Pricing

Runs are billed usage-based from your workspace credit balance — the cost of a job is the sum of the model token (and any media) usage it incurs. There is no per-call platform fee. The playground and the job result report the exact cost of each run.

- Pricing page: https://puras.co/pricing
- Machine-readable model price registry: `https://api.puras.co/v1/pricing`