# Seedream V4.5 Image Editing

> Advanced image editing model by ByteDance that uses text prompts and up to 10 reference images to stylize, transform, and seamlessly composite visuals.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/bytedance/seedream-v4.5/edit`
- **Model ID**: `bytedance/seedream-v4.5/edit`
- **Category**: image-to-image
- **Kind**: inference
- **Tags**: image, image-to-image, image editing, bytedance, seedream, stylized, transform

## Pricing

- **Price**: $0.04 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-v4.5/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-v4.5/edit/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/bytedance/seedream-v4.5/edit/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/bytedance/seedream-v4.5/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

- **`seed`** (`integer`, _optional_):
  Random seed to control the stochasticity of image generation.

- **`prompt`** (`string`, _required_):
  The text prompt used to edit the image.

- **`image_size`** (`ImageSize | image_size_enum`, _optional_):
  The size of the generated image. Use a preset string (e.g. '4_3_1k') or a custom {width, height} object.
  - Default: `"4_3_2k"`
  - Options: `"1_1_512"`, `"1_1_1k"`, `"1_1_2k"`, `"1_1_4k"`, `"16_9_512"`, `"16_9_1k"`, `"16_9_2k"`, `"16_9_4k"`, `"9_16_512"`, `"9_16_1k"`, `"9_16_2k"`, `"9_16_4k"`, `"4_3_512"`, `"4_3_1k"`, `"4_3_2k"`, `"4_3_4k"`, `"3_4_512"`, `"3_4_1k"`, `"3_4_2k"`, `"3_4_4k"`, `"3_2_512"`, `"3_2_1k"`, `"3_2_2k"`, `"3_2_4k"`, `"2_3_512"`, `"2_3_1k"`, `"2_3_2k"`, `"2_3_4k"`, `"4_5_512"`, `"4_5_1k"`, `"4_5_2k"`, `"4_5_4k"`, `"5_4_512"`, `"5_4_1k"`, `"5_4_2k"`, `"5_4_4k"`, `"4_1_512"`, `"4_1_1k"`, `"4_1_2k"`, `"4_1_4k"`, `"1_4_512"`, `"1_4_1k"`, `"1_4_2k"`, `"1_4_4k"`, `"8_1_512"`, `"8_1_1k"`, `"8_1_2k"`, `"8_1_4k"`, `"1_8_512"`, `"1_8_1k"`, `"1_8_2k"`, `"1_8_4k"`, `"21_9_512"`, `"21_9_1k"`, `"21_9_2k"`, `"21_9_4k"`, `"auto"`

- **`image_urls`** (`array<string>`, _required_):
  List of URLs of input images for editing. Presently, up to 10 image inputs are allowed. If over 10 images are sent, only the last 10 will be used.

- **`num_images`** (`integer`, _optional_):
  The number of images to generate. Each generated image is billed.
  - Default: `1`
  - Range: `1` to `4`

- **`enable_safety_checker`** (`boolean`, _optional_):
  If set to true, the safety checker will be enabled. This setting can only be configured via the API.
  - Default: `true`

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "seed": 841920,
  "prompt": "Place the sunflower vase from the second image onto the center of the wooden coffee table from the first image. Ensure the lighting matches the bright living room and casts realistic shadows on the wood surface.",
  "image_size": "auto_4K",
  "image_urls": [
    "https://media.modelrunner.ai/tuI1u7vLynspoSrwOi8D2.png",
    "https://media.modelrunner.ai/A7XjPSntU3DuZMWM7uvHK.png"
  ],
  "max_images": 2,
  "num_images": 2,
  "enable_safety_checker": true
}
```

**Output**

```json
[
  "https://media.modelrunner.ai/MOKdoPEQsVitDNc0IIa18.png",
  "https://media.modelrunner.ai/w03LFM74zhFDlw4R055S9.png",
  "https://media.modelrunner.ai/udxcKgrkxAwnVk1wbr66I.png",
  "https://media.modelrunner.ai/PYrY72sl7oZk0uLZtyybb.png"
]
```
## 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-v4.5/edit \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "seed": 841920,
  "prompt": "Place the sunflower vase from the second image onto the center of the wooden coffee table from the first image. Ensure the lighting matches the bright living room and casts realistic shadows on the wood surface.",
  "image_size": "auto_4K",
  "image_urls": [
    "https://media.modelrunner.ai/tuI1u7vLynspoSrwOi8D2.png",
    "https://media.modelrunner.ai/A7XjPSntU3DuZMWM7uvHK.png"
  ],
  "max_images": 2,
  "num_images": 2,
  "enable_safety_checker": true
}')

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-v4.5/edit", {
  input: {
  "seed": 841920,
  "prompt": "Place the sunflower vase from the second image onto the center of the wooden coffee table from the first image. Ensure the lighting matches the bright living room and casts realistic shadows on the wood surface.",
  "image_size": "auto_4K",
  "image_urls": [
    "https://media.modelrunner.ai/tuI1u7vLynspoSrwOi8D2.png",
    "https://media.modelrunner.ai/A7XjPSntU3DuZMWM7uvHK.png"
  ],
  "max_images": 2,
  "num_images": 2,
  "enable_safety_checker": true
}
});

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

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "bytedance/seedream-v4.5/edit",
        arguments={
  "seed": 841920,
  "prompt": "Place the sunflower vase from the second image onto the center of the wooden coffee table from the first image. Ensure the lighting matches the bright living room and casts realistic shadows on the wood surface.",
  "image_size": "auto_4K",
  "image_urls": [
    "https://media.modelrunner.ai/tuI1u7vLynspoSrwOi8D2.png",
    "https://media.modelrunner.ai/A7XjPSntU3DuZMWM7uvHK.png"
  ],
  "max_images": 2,
  "num_images": 2,
  "enable_safety_checker": true
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/bytedance/seedream-v4.5/edit)
- [OpenAPI Schema](https://modelrunner.ai/models/bytedance/seedream-v4.5/edit/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/bytedance/seedream-v4.5/edit/llms.txt)