# Seedream 5.0 Pro Image Editing

> Edit, restyle, and composite images from a text prompt and up to 10 reference images — the premium precision-editing tier of Seedream 5.0.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/bytedance/seedream-v5-pro/edit`
- **Model ID**: `bytedance/seedream-v5-pro/edit`
- **Category**: image-to-image
- **Kind**: inference
- **Tags**: image, image-to-image, image editing, bytedance, seedream, pro

## Pricing

- **Price**: $0.09 per output

## Request Lifecycle

This model runs on the ModelRunner **asynchronous queue API** — a single POST does not return the output. Every call requires an `Authorization: Key $MODEL_RUNNER_KEY` header. Run three steps:

1. **Submit** — `POST https://queue.modelrunner.run/bytedance/seedream-v5-pro/edit` with a JSON body holding the input fields at the top level. The body may also include a reserved top-level `metadata` object — a flat string map (max 16 keys, key ≤64 / value ≤512 chars) stored on the request for your own tagging. It is never sent to the model; filter your request history with `GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>` (exact key=value matches, AND-ed). The response carries request handles only (no output yet):

```json
{
  "status": "IN_QUEUE",
  "request_id": "<21-char id>",
  "status_url": "https://queue.modelrunner.run/bytedance/seedream-v5-pro/edit/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/bytedance/seedream-v5-pro/edit/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/bytedance/seedream-v5-pro/edit/requests/<request_id>/cancel"
}
```

2. **Poll status** — `GET <status_url>` until `status` is `COMPLETED`. Possible values are `IN_QUEUE`, `IN_PROGRESS`, `COMPLETED`, `FAILED`, `CANCELLED`. A `FAILED` request responds with HTTP 400 and an `error` field.

3. **Read result** — `GET <response_url>`. Returns the finished request, including the generated `output`:

```json
{ "id": "<request_id>", "status": "COMPLETED", "output": ..., "input": ... }
```

The JavaScript and Python SDKs below perform steps 2–3 for you. In any language without an SDK (Swift, Go, Kotlin, etc.) you must implement the polling loop and the final result fetch yourself — see the cURL example for the full flow.

### Input Schema

- **`size`** (`SizeEnum`, _optional_):
  Output image dimensions as WxH pixels. Values at or below ~2.36 megapixels (e.g. 1024x1024, 1376x768) bill at the lower price tier; higher-resolution values (e.g. 2048x2048) bill at the premium tier.
  - Default: `"1024x1024"`
  - Options: `"1024x1024"`, `"1376x768"`, `"768x1376"`, `"1264x848"`, `"848x1264"`, `"1200x896"`, `"896x1200"`, `"2048x2048"`, `"2752x1536"`, `"1536x2752"`, `"2528x1696"`, `"1696x2528"`, `"2400x1792"`, `"1792x2400"`

- **`prompt`** (`string`, _required_):
  Text prompt describing the edit to apply to the reference image(s).

- **`image_urls`** (`array<string>`, _required_):
  Reference image(s) to edit or use for reference-based generation. Required — provide 1 to 10 images.

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "size": "1024x1024",
  "prompt": "Fill the white mug with a cappuccino topped with delicate leaf latte art, and add a golden-brown croissant on a small ceramic plate beside the leather notebook. Keep the desk, lighting, and composition identical.",
  "image_urls": [
    "https://media.modelrunner.ai/XMv4k5cqfBIGGydmqJgi3.jpeg"
  ]
}
```

**Output**

```json
[
  "https://media.modelrunner.ai/lphLSoPoMSlqAr1BfIALH.jpeg"
]
```
## Usage Examples

### cURL

The queue API is asynchronous: submit the request, poll `status_url` until it is `COMPLETED`, then read the result from `response_url`. Requires `jq`.

```bash
# 1. Submit the request (returns request handles, not the output)
SUBMIT=$(curl --silent --request POST \
  --url https://queue.modelrunner.run/bytedance/seedream-v5-pro/edit \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "size": "1024x1024",
  "prompt": "Fill the white mug with a cappuccino topped with delicate leaf latte art, and add a golden-brown croissant on a small ceramic plate beside the leather notebook. Keep the desk, lighting, and composition identical.",
  "image_urls": [
    "https://media.modelrunner.ai/XMv4k5cqfBIGGydmqJgi3.jpeg"
  ]
}')

STATUS_URL=$(echo "$SUBMIT" | jq -r '.status_url')
RESPONSE_URL=$(echo "$SUBMIT" | jq -r '.response_url')

# 2. Poll until the request leaves the queue / in-progress state
while true; do
  STATUS=$(curl --silent --url "$STATUS_URL" \
    --header "Authorization: Key $MODEL_RUNNER_KEY" | jq -r '.status')
  echo "Status: $STATUS"
  case "$STATUS" in
    COMPLETED) break ;;
    FAILED|CANCELLED) echo "Request $STATUS"; exit 1 ;;
  esac
  sleep 1
done

# 3. Read the finished request, including the generated output
curl --silent --url "$RESPONSE_URL" \
  --header "Authorization: Key $MODEL_RUNNER_KEY"
```

### JavaScript

```javascript
import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("bytedance/seedream-v5-pro/edit", {
  input: {
  "size": "1024x1024",
  "prompt": "Fill the white mug with a cappuccino topped with delicate leaf latte art, and add a golden-brown croissant on a small ceramic plate beside the leather notebook. Keep the desk, lighting, and composition identical.",
  "image_urls": [
    "https://media.modelrunner.ai/XMv4k5cqfBIGGydmqJgi3.jpeg"
  ]
}
});

console.log(result.data);
```

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "bytedance/seedream-v5-pro/edit",
        arguments={
  "size": "1024x1024",
  "prompt": "Fill the white mug with a cappuccino topped with delicate leaf latte art, and add a golden-brown croissant on a small ceramic plate beside the leather notebook. Keep the desk, lighting, and composition identical.",
  "image_urls": [
    "https://media.modelrunner.ai/XMv4k5cqfBIGGydmqJgi3.jpeg"
  ]
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/bytedance/seedream-v5-pro/edit)
- [OpenAPI Schema](https://modelrunner.ai/models/bytedance/seedream-v5-pro/edit/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/bytedance/seedream-v5-pro/edit/llms.txt)