# Phota Edit (`phota/edit`)

> Phota image editing. Edit existing images with text prompts.

- Capability: Images (tool `image`) — Image to image
- Price: from $0.09 per run (1 credit = $0.01). Exact price for a request: POST https://api.varg.ai/v2/estimate
- Typical time: ~15 s
- JSON Schema: https://api.varg.ai/v2/tools/image?model=phota%2Fedit (public, no key)
- Try it: https://varg.ai/dashboard/tools/playground?model=phota%2Fedit

## Call it

REST: `POST https://api.varg.ai/v2/tools/image/call` with `Authorization: Bearer $VARG_API_KEY` (create a key at https://varg.ai/dashboard/api).
It answers `202` with a job right away. Poll `GET /v2/jobs/{id}` until `status` is `completed`, then read `output.outputs[0].url` — or pass `options.webhook_url` and get the finished job POSTed to you.

```bash
curl -X POST https://api.varg.ai/v2/tools/image/call \
  -H "Authorization: Bearer $VARG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "phota/edit",
  "prompt": "Keep the EXACT same woman and identity from the reference images — do NOT change her face. Keep the same cozy warm candle-lit room (bookshelf, plants, lamp, warm ambient light). Make TWO changes only: (1) her MOUTH IS CLOSED — calm, gentle, warm closed-lip soft smile, lips together, relaxed natural expression. (2) Change her knit sweater to a soft LIGHT SUMMER color palette — a cool, light, muted pastel such as dusty rose, soft powder blue, or soft lavender-grey (pick the most flattering), cozy knit. Keep light natural retouch and subtle natural eye makeup. Photorealistic, candid phone-reel look, front-facing, looking at the camera, head and shoulders. Aspect ratio 9:16 vertical.",
  "files": [
    {
      "url": "https://s3.varg.ai/u/f3d2a9a3-60a1-417c-999d-35e3cd6678da/tmp_402c16ae-028.jpg"
    },
    {
      "url": "https://s3.varg.ai/u/f3d2a9a3-60a1-417c-999d-35e3cd6678da/tmp_73d59075-140.png"
    },
    {
      "url": "https://s3.varg.ai/u/f3d2a9a3-60a1-417c-999d-35e3cd6678da/tmp_4e062ea5-da0.jpg"
    }
  ]
}'
```

MCP: the varg server `https://mcp.varg.ai/mcp` (OAuth sign-in, no key) runs it with `call_tool`:

```json
{
  "tool": "image",
  "input": {
    "model": "phota/edit",
    "prompt": "Keep the EXACT same woman and identity from the reference images — do NOT change her face. Keep the same cozy warm candle-lit room (bookshelf, plants, lamp, warm ambient light). Make TWO changes only: (1) her MOUTH IS CLOSED — calm, gentle, warm closed-lip soft smile, lips together, relaxed natural expression. (2) Change her knit sweater to a soft LIGHT SUMMER color palette — a cool, light, muted pastel such as dusty rose, soft powder blue, or soft lavender-grey (pick the most flattering), cozy knit. Keep light natural retouch and subtle natural eye makeup. Photorealistic, candid phone-reel look, front-facing, looking at the camera, head and shoulders. Aspect ratio 9:16 vertical.",
    "files": [
      {
        "url": "https://s3.varg.ai/u/f3d2a9a3-60a1-417c-999d-35e3cd6678da/tmp_402c16ae-028.jpg"
      },
      {
        "url": "https://s3.varg.ai/u/f3d2a9a3-60a1-417c-999d-35e3cd6678da/tmp_73d59075-140.png"
      },
      {
        "url": "https://s3.varg.ai/u/f3d2a9a3-60a1-417c-999d-35e3cd6678da/tmp_4e062ea5-da0.jpg"
      }
    ]
  },
  "wait": true
}
```

## Inputs

| field | type | required | default | allowed | description |
|---|---|---|---|---|---|
| `model` | string | yes | — | `phota/edit` or a route key below | Which model runs the job. |
| `prompt` | string | no | — | — | — |
| `files` | array of { url } | no | — | — | — |
| `aspect_ratio` | string | no | — | e.g. 16:9 \| 9:16 \| 1:1 \| 4:3 \| 3:4 \| 21:9 \| auto | — |

Media inputs are URLs. Upload a local file first with `POST /v2/files` and pass the returned URL.

## Provider options

Optional, per provider, under `provider_options.<provider>`. Only the options of the provider that runs the job apply — pin a route to choose it.

### provider_options.fal

| field | type | required | default | allowed | description |
|---|---|---|---|---|---|
| `prompt` | string | no | — | — | Text description of the desired image. To refer to specific profiles, use [[profile_id_1]], [[profile_id_2]], etc. |
| `image_urls` | array of URL strings | no | — | — | — |
| `profile_ids` | array of URL strings | no | — | — | — |
| `sync_mode` | boolean | no | — | — | If `True`, the media will be returned as a data URI and the output data won't be available in the request history. |
| `num_images` | integer | no | — | 1–4 | Number of images to generate. |
| `resolution` | string | no | — | 1K \| 4K | — |
| `aspect_ratio` | string | no | — | auto \| 1:1 \| 16:9 \| 4:3 \| 3:4 \| 9:16 | — |
| `output_format` | string | no | — | jpeg \| png | — |

## Routes

`"model": "phota/edit"` picks a route automatically (priority order, then the inputs you send). To pin one, pass its key as `model`.

| model key | provider | modality | price from | typical time |
|---|---|---|---|---|
| `fal:phota/edit` | fal | image-to-image | $0.09 | ~15 s |

## Example output

- image/jpeg: https://s3.varg.ai/o/job_12eb4a10.jpg

---

Catalog version 2026-11-11T12:59:09.901887+00:00. All models: https://varg.ai/models/llms.txt