Extract frames from a video

Save up to 20 frames of a video as pictures, evenly spaced or one per scene. Made for showing a video to a vision model.

Input

Choose a file or drop it here

Up to 100 MB.

The video to take frames from.
How many frames to save, at most.
even spreads the frames over the video. scenes saves the first frame of each scene.
Picture format of the frames. JPG is small; PNG keeps every pixel exactly.
Largest width of each frame in pixels. Left empty, frames keep the size of the video.
Only look at the video from this time on, in seconds.
Only look at the video up to this time, in seconds.
For scenes mode: how big a change counts as a new scene, from 0.05 (small changes) to 0.95 (only hard cuts).
Return one zip archive holding the frames instead of separate picture files.

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.mp4 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/video-frames \
  -H 'Content-Type: application/json' \
  -d '{"input":{"video":"DROP_ID/f1","count":4},"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": {'video': upload("sample.mp4"), 'count': 4}, "wait": 30}
reply = call("POST", "/v1/tools/video-frames", 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/video-frames`, {
  method: "POST",
  headers: {"Content-Type": "application/json"},
  body: JSON.stringify({input: {"video":await upload(file, "sample.mp4"),"count":4}, 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.mp4",
      "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": "video-frames",
  "input": {
    "video": "DROP_ID/f1",
    "count": 4
  }
}

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": {
    "video": "DROP_ID/f1",
    "count": 4
  },
  "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/video-frames. Over MCP: run_tool with slug: "video-frames". Machine-readable: input schema, Markdown. Connect an agent.

Inputs

NameTypeRequiredWhat it does
video file yes The video to take frames from. In the API: a file reference such as DROP_ID/f1. Accepts: video.
count integer no How many frames to save, at most. Default: 8. From 1 to 20.
mode string no even spreads the frames over the video. scenes saves the first frame of each scene. One of: even, scenes. Default: "even".
format string no Picture format of the frames. JPG is small; PNG keeps every pixel exactly. One of: jpg, png. Default: "jpg".
width integer no Largest width of each frame in pixels. Left empty, frames keep the size of the video. From 16 to 3840.
start number no Only look at the video from this time on, in seconds. Default: 0.
end number no Only look at the video up to this time, in seconds.
threshold number no For scenes mode: how big a change counts as a new scene, from 0.05 (small changes) to 0.95 (only hard cuts). Default: 0.3. From 0.05 to 0.95.
zip boolean no Return one zip archive holding the frames instead of separate picture files. Default: false.

Examples

Four evenly spaced frames

Input
{
  "video": "sample.mp4",
  "count": 4
}
Result

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

One frame per scene, as small PNGs

Input
{
  "video": "sample.mp4",
  "count": 6,
  "mode": "scenes",
  "format": "png",
  "width": 160
}
Result

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

Five frames in one zip

Input
{
  "video": "sample.mp4",
  "count": 5,
  "zip": true
}
Result

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

Questions

How do I show a video to an AI model?
Most vision models read pictures, not video. Save 8 to 20 frames here and send them in order together with the times given in the result. For a single picture of the whole video, use video-contact-sheet.
Which mode should I use?
even is predictable and good for steady footage. scenes follows the cuts, so an edited video gets one frame for each shot. If no cuts are found, evenly spaced frames are saved instead.
Why did I get fewer frames than I asked for?
A very short video has fewer frames than the count, and scenes mode saves only as many frames as it finds scenes.