Remove a solid background
Make a plain, single-colour background transparent, for logos, icons, scans and product shots.
Input
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.png 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-remove-background \
-H 'Content-Type: application/json' \
-d '{"input":{"image":"DROP_ID/f1"},"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.png")}, "wait": 30}
reply = call("POST", "/v1/tools/image-remove-background", 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(`${BASE}/v1/tools/image-remove-background`, {
method: "POST",
headers: {"Content-Type": "application/json"},
body: JSON.stringify({input: {"image":await upload(file, "sample.png")}, wait: 30}),
})).json();
// Step 3: a job that is still running comes back as {job}. Wait for it.
while (!reply.result && ["queued", "running"].includes((reply.job || reply).status)) {
reply = await (await fetch(`${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.png",
"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-remove-background",
"input": {
"image": "DROP_ID/f1"
}
}
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"
},
"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-remove-background. Over MCP: run_tool with slug: "image-remove-background".
Machine-readable: input schema, Markdown. Connect an agent.
Inputs
| Name | Type | Required | What it does |
|---|---|---|---|
image |
file | yes | The image with a plain background. In the API: a file reference such as DROP_ID/f1. Accepts: image. |
color |
string | no | The background colour to remove, as a hex colour or colour name. Leave empty to take it from the corners of the image. Default: "". |
tolerance |
integer | no | How close a colour must be to count as background: 0 is an exact match, 100 matches everything. Default: 10. From 0 to 100. |
feather |
integer | no | Soften the cut edge over this many pixels. 0 leaves a hard edge. Default: 0. From 0 to 20. |
contiguous |
boolean | no | Only remove background connected to the edge of the image, so the same colour inside the subject is kept. Turn off to remove the colour everywhere. Default: true. |
format |
string | no | File format of the result. Both keep transparency. One of: png, webp. Default: "png". |
Examples
Remove the colour found in the corners
{
"image": "sample.png"
}Press the example button above to run it on the sample file.
Remove white everywhere, with a soft edge
{
"image": "sample.jpg",
"color": "#ffffff",
"tolerance": 20,
"feather": 1,
"contiguous": false
}Press the example button above to run it on the sample file.
Questions
- Does this work on photos?
- Only if the background is one flat colour, such as a white studio backdrop or a green screen. It matches a colour; it does not recognise people or objects. Busy or graduated backgrounds need a dedicated cut-out program.
- Parts of my subject became transparent. Why?
- They are close to the background colour and touch the edge of it. Lower the tolerance, and keep contiguous on so matching colours inside the subject survive.
- There is a thin halo around the subject. What helps?
- Raise the tolerance a little and set feather to 1 or 2 to soften the edge.
- How is the background colour chosen?
- From the four corner pixels: the colour most of them share. Give "color" yourself if the corners are not background.
Related tools
- Convert image formatConvert an image between PNG, JPG, WebP, AVIF, GIF, BMP, TIFF and ICO. Animated GIF and WebP stay animated.
image-convert - Add padding or a borderAdd padding, margin or a coloured border around an image, the same on every side or set per side.
image-pad - Colour palette from an imageExtract the dominant colours of an image as hex and RGB values with their share, plus a swatch image.
image-palette - Add a text watermarkAdd a text watermark to an image in a corner, in the centre or tiled across it, with adjustable opacity and size.
image-watermark - Add text to an imageWrite text on an image at a position you choose, with size, colour, an outline or a background box. Multi-line.
image-text-overlay - Adjust brightness, contrast and colourAdjust the brightness, contrast, saturation, sharpness and gamma of an image. 1 leaves a setting unchanged.
image-adjust