Add text to an image

Write text on an image at a position you choose, with size, colour, an outline or a background box. Multi-line.

Input

Choose a file or drop it here

You can also paste an image. Up to 100 MB.

The image to write on.
The text to draw. Use line breaks (or \n) for several lines. Latin, Greek or Cyrillic letters, digits and punctuation.
Left edge of the text, in pixels from the left of the image. Leave empty to use position.
Top edge of the text, in pixels from the top of the image. Leave empty to use position.
Where to put the text when x or y is not given.
Height of the text in pixels.
Colour of the text. Add two more hex digits for see-through text, such as #ffffff80. A hex colour such as #ff8800, or a name such as white or black.
Colour of a thin outline around the letters, which keeps text readable on busy pictures. Leave empty for none.
Colour of a filled box behind the text, for example #00000080 for half-transparent black. Leave empty for none.

Result

Choose a file and press Run.

Files you upload and the results are stored for one hour, then deleted. Anyone who has the link can open them, so don't upload anything private.

Use it from code or an agent

# 1. Upload the file. The reply ends with a line "ref  <id>/f1": that is the file reference.
curl -T sample.jpg https://setget.net/drop/

# 2. Run the tool with that reference. "wait" holds the reply for up to 30 seconds while the job runs.
curl -s https://setget.net/v1/tools/image-text-overlay \
  -H 'Content-Type: application/json' \
  -d '{"input":{"image":"DROP_ID/f1","text":"Hello world"},"wait":30}'

# 3. The reply is {"tool", "ms", "result", "files": [{"name", "size", "url", "ref"}], "job"}.
#    Download a result file from its "url", or pass its "ref" to another tool.
#    Still running after the wait? The reply is 202 with "job": follow it with
#    curl -s https://setget.net/v1/jobs/JOB_ID?wait=30
import json, urllib.parse, urllib.request

BASE = "https://setget.net"

def call(method, path, body=None, headers=None):
    request = urllib.request.Request(BASE + path, body, headers or {}, method=method)
    return json.load(urllib.request.urlopen(request))

def upload(path):
    """Step 1: upload a file and get its reference."""
    name = path.replace("\\", "/").rsplit("/", 1)[-1]
    with open(path, "rb") as handle:
        reply = call("PUT", "/drop/" + urllib.parse.quote(name), handle.read(), {"Accept": "application/json"})
    return reply["file"]["ref"]

# Step 2: run the tool with the reference.
body = {"input": {'image': upload("sample.jpg"), 'text': 'Hello world'}, "wait": 30}
reply = call("POST", "/v1/tools/image-text-overlay", json.dumps(body).encode(), {"Content-Type": "application/json"})

# Step 3: a job that is still running comes back as {"job": ...}. Wait for it.
while "result" not in reply and reply.get("job", reply).get("status") in ("queued", "running"):
    reply = call("GET", "/v1/jobs/" + reply.get("job", reply)["id"] + "?wait=30")
if "error" in reply:
    raise SystemExit(reply["error"]["message"])
print(reply["result"])
for file in reply["files"]:   # result files: download from "url", or pass "ref" to another tool
    print(file["name"], file["size"], file["url"], file["ref"])
const BASE = "https://setget.net";

// Step 1: upload a file and get its reference. file: a File or Blob
// (in Node: new Blob([fs.readFileSync(path)])).
async function upload(file, name) {
  const response = await fetch(`${BASE}/drop/${encodeURIComponent(name)}`, {
    method: "PUT", headers: {Accept: "application/json"}, body: file,
  });
  return (await response.json()).file.ref;
}

// Step 2: run the tool with the reference.
let reply = await (await fetch(`${BASE}/v1/tools/image-text-overlay`, {
  method: "POST",
  headers: {"Content-Type": "application/json"},
  body: JSON.stringify({input: {"image":await upload(file, "sample.jpg"),"text":"Hello world"}, wait: 30}),
})).json();

// Step 3: a job that is still running comes back as {job}. Wait for it.
while (!reply.result && ["queued", "running"].includes((reply.job || reply).status)) {
  reply = await (await fetch(`${BASE}/v1/jobs/${(reply.job || reply).id}?wait=30`)).json();
}
if (reply.error) throw new Error(reply.error.message);
console.log(reply.result);
for (const file of reply.files) console.log(file.name, file.size, file.url, file.ref);
1. Upload. Tool: drop
Arguments:
{
  "action": "create",
  "files": [
    {
      "name": "sample.jpg",
      "size": "<bytes>"
    }
  ]
}
PUT each file's bytes to its "upload.url" with the listed headers, and keep its "ref".
With a shell, one command does both: curl -T FILE https://setget.net/drop/

2. Run. Tool: run_tool
Arguments:
{
  "slug": "image-text-overlay",
  "input": {
    "image": "DROP_ID/f1",
    "text": "Hello world"
  }
}

3. The answer holds "result" and "files" (each with "url" and "ref").
If it holds a "job" that is still running instead, follow it. Tool: job
Arguments:
{
  "action": "wait",
  "id": "JOB_ID"
}
{
  "input": {
    "image": "DROP_ID/f1",
    "text": "Hello world"
  },
  "wait": 30
}

This is a file tool, so a call takes three steps: upload the file to get a reference, run the tool with that reference, then read the result and download its files. Uploads and results are public by link and expire after one hour.

Endpoint: POST /v1/tools/image-text-overlay. Over MCP: run_tool with slug: "image-text-overlay". Machine-readable: input schema, Markdown. Connect an agent.

Inputs

NameTypeRequiredWhat it does
image file yes The image to write on. In the API: a file reference such as DROP_ID/f1. Accepts: image.
text string yes The text to draw. Use line breaks (or \n) for several lines. Latin, Greek or Cyrillic letters, digits and punctuation.
x integer no Left edge of the text, in pixels from the left of the image. Leave empty to use position.
y integer no Top edge of the text, in pixels from the top of the image. Leave empty to use position.
position string no Where to put the text when x or y is not given. One of: top-left, top, top-right, left, center, right, bottom-left, bottom, bottom-right. Default: "center".
size integer no Height of the text in pixels. Default: 32. From 6 to 1000.
color string no Colour of the text. Add two more hex digits for see-through text, such as #ffffff80. A hex colour such as #ff8800, or a name such as white or black. Default: "#ffffff".
outline string no Colour of a thin outline around the letters, which keeps text readable on busy pictures. Leave empty for none.
box string no Colour of a filled box behind the text, for example #00000080 for half-transparent black. Leave empty for none.

Examples

Centred text

Input
{
  "image": "sample.jpg",
  "text": "Hello world"
}
Result

Press the example button above to run it on the sample file.

Two outlined lines at the bottom

Input
{
  "image": "sample.jpg",
  "text": "Top line\nSecond line",
  "position": "bottom",
  "size": 28,
  "outline": "#000000"
}
Result

Press the example button above to run it on the sample file.

On a dark box at a fixed spot

Input
{
  "image": "sample.png",
  "text": "SALE",
  "x": 20,
  "y": 20,
  "size": 48,
  "color": "#ffffff",
  "box": "#000000cc"
}
Result

Press the example button above to run it on the sample file.

Questions

How do I keep text readable on any picture?
Add an outline in a contrasting colour (white text with a black outline works on almost anything), or put a half-transparent box behind it.
Which characters can I use?
Latin letters including accents, Greek, Cyrillic, digits and punctuation. Chinese, Japanese, Korean, Arabic and emoji are not supported yet; the tool tells you which characters it cannot draw.
Can I choose the font?
Not yet. One clean sans-serif font is built in.
What if the text does not fit?
It is drawn at the size you asked for and cut off at the edge of the image. The result says when that happened, with the space the text needed.