Skip to main content
ModelRunner
bytedance avatar

Seedream 5.0 Pro Image Editing API

bytedance/seedream-v5-pro/edit

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

edit
0.09
OpenAPI

Model Input

Input

Text prompt describing the edit to apply to the reference image(s).

  • https://media.modelrunner.ai/XMv4k5cqfBIGGydmqJgi3.jpeg

Reference image(s) to edit or use for reference-based generation. Required — provide 1 to 10 images.

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.

You need to be logged in to run this model and view results.
Log in

Model Output

Output

Generated image output
Generated in 121.674 seconds
Logs (1 lines)

Model Example Requests

Examples

Example output 1Example output 2Example output 3

Seedream 5.0 Pro Image Editing API

Seedream 5.0 Pro Image Editing is a image-to-image AI model by bytedance. On ModelRunner it runs through a REST API or via MCP from any AI assistant, at $0.09 per image.

POST https://queue.modelrunner.run/bytedance/seedream-v5-pro/edit

cURL

# Submit a request to the queue. Input fields go at the top level of the
# body. The optional reserved "metadata" object holds your own flat string
# tags — stored on the request, never sent to the model; filter later with
# GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>.
curl -X POST https://queue.modelrunner.run/bytedance/seedream-v5-pro/edit \
  -H "Authorization: Key $MRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "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…",
    "image_urls": [
      "https://media.modelrunner.ai/XMv4k5cqfBIGGydmqJgi3.jpeg"
    ],
    "metadata": {
      "project": "my-project"
    }
  }'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }

# Poll status_url until "COMPLETED", then fetch the result
curl "https://queue.modelrunner.run/bytedance/seedream-v5-pro/edit/requests/$REQUEST_ID/status" \
  -H "Authorization: Key $MRUN_API_KEY"
curl "https://queue.modelrunner.run/bytedance/seedream-v5-pro/edit/requests/$REQUEST_ID" \
  -H "Authorization: Key $MRUN_API_KEY"

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…",
    "image_urls": [
      "https://media.modelrunner.ai/XMv4k5cqfBIGGydmqJgi3.jpeg"
    ]
  },
});
console.log(result);

Python

import os
import requests

headers = {"Authorization": f"Key {os.environ['MRUN_API_KEY']}"}

submitted = requests.post(
    "https://queue.modelrunner.run/bytedance/seedream-v5-pro/edit",
    headers=headers,
    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…",
      "image_urls": [
        "https://media.modelrunner.ai/XMv4k5cqfBIGGydmqJgi3.jpeg"
      ]
    },
).json()

# Poll submitted["status_url"] until "COMPLETED", then:
result = requests.get(submitted["response_url"], headers=headers).json()

Input parameters

NameTypeRequiredDescription
promptstringyesText prompt describing the edit to apply to the reference image(s).
image_urlsarrayyesReference image(s) to edit or use for reference-based generation. Required — provide 1 to 10 images.
sizeenumnoOutput 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".

Machine-readable: OpenAPI schema · llms.txt

Use Seedream 5.0 Pro Image Editing from Claude & Cursor (MCP)

Point Claude Code, Claude Desktop, Cursor, or any MCP client at the ModelRunner MCP server and Seedream 5.0 Pro Image Editing becomes a tool your assistant can call directly — it authorizes via OAuth (no API key in config) and runs this model with the run_model tool using the endpoint bytedance/seedream-v5-pro/edit.

MCP client config (Claude Desktop, Cursor)

{
  "mcpServers": {
    "modelrunner": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.modelrunner.run/mcp"]
    }
  }
}

Claude Code

claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcp

Then ask your assistant, for example: “Run bytedance/seedream-v5-pro/edit on ModelRunner to generate image”. MCP setup guide.

Model Details

Model Details

Seedream 5.0 Pro Image Editing is the premium tier of the Seedream 5.0 image line, focused on reference-based image editing. Provide one to ten reference images plus a text instruction and it edits, restyles, or composites existing visuals with high fidelity and precise instruction following. It keeps subjects, identity, and product details consistent across references, renders accurate in-image text, and outputs from roughly 1 up to ~4.2 megapixels (2K). Larger output sizes cost more per image.

## Best for - Editing or restyling a photo from a text instruction while keeping the rest of the image unchanged - Reference-based generation: transferring style, identity, or product details from up to 10 reference images - Compositing multiple products, people, or scenes into one coherent image - Adding, removing, or replacing objects in an existing image - Premium-quality edits where detail and instruction accuracy matter more than speed or price

## Choose another model when - You want to generate an image from a prompt with no reference image — use `bytedance/seedream-v5-pro/text-to-image` - You want the fastest, cheapest editing and can trade some quality — use the Lite tier `bytedance/seedream-v5/edit` - You need several images from one call — this tier returns a single image per request - You need a video rather than a still image — use an image-to-video model

## Tips - Pass the source image(s) in `image_urls` and describe the change precisely, stating what should stay unchanged - Provide clear, high-resolution reference images; you can supply up to 10 - `size` sets both resolution and aspect ratio; pick a ~1MP value (e.g. `1024x1024`) for the lower price tier, or a 2K value (e.g. `2048x2048`) for maximum detail at the premium tier - Put any text you want rendered inside quotation marks in the prompt for the most accurate spelling

To run via the ModelRunner JavaScript client: ```js import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("bytedance/seedream-v5-pro/edit", { input: { prompt: "replace the background with a sunlit studio, keep the subject unchanged", image_urls: ["https://media.modelrunner.ai/example-photo.jpg"], size: "1024x1024", }, }); ```