Character Swap – Analyze

namifusion/character-swap/analyze

Detect and track every person in a video with SAM3. Returns a character list with preview images and a track manifest for the generate step.

Parameters

NameTypeDefaultConstraintsDescription
resolutionResolutionselect720p480p | 720pSelects the output resolution or provider generation mode. Higher settings may take longer to process.

Output fields

FieldTypeDescription
objectsarrayDetected characters: obj_id, preview url, masked_url, coverage, representative_frame, bbox
video_infoobjectInput video info: width/height/fps/frame_count
analysis_idstringAnalysis session id
detected_objectsnumberNumber of detected characters
track_manifest_urlstringTrack manifest URL - pass it to the generate model

API

Call this model through one unified REST API. Get a key on the API Keys page.

cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/namifusion/character-swap/analyze" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "resolution": "720p"
  }
}'

# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
  -H "Authorization: Bearer YOUR_API_KEY"
Python
import time, requests

API_KEY = "YOUR_API_KEY"
HEADERS = {"Authorization": f"Bearer {API_KEY}"}

# 1) Submit
resp = requests.post(
    "https://www.namifusion.com/api/v1/marketplace/run/namifusion/character-swap/analyze",
    headers=HEADERS,
    json={
        "input": {
            "resolution": "720p"
        }
    },
)
resp.raise_for_status()  # 401/402/429/5xx stop here instead of polling a bad task
task = resp.json()

# 2) Poll until a terminal state (completed / failed / cancelled).
#    This model is allowed up to 1800s server-side.
deadline = time.time() + 1860
while task.get("status") not in ("completed", "failed", "cancelled"):
    if time.time() > deadline:
        raise TimeoutError(f"still {task.get('status')} — keep the task_uuid and poll later")
    time.sleep(3)
    poll = requests.get(f"https://www.namifusion.com/api/v1/marketplace/run/tasks/{task['task_uuid']}", headers=HEADERS)
    poll.raise_for_status()
    task = poll.json()

print(task["status"], task.get("output"))
JavaScript
const API_KEY = "YOUR_API_KEY";
const HEADERS = { Authorization: `Bearer ${API_KEY}` };

// 1) Submit
const resp = await fetch("https://www.namifusion.com/api/v1/marketplace/run/namifusion/character-swap/analyze", {
  method: "POST",
  headers: { ...HEADERS, "Content-Type": "application/json" },
  body: JSON.stringify({
    "input": {
      "resolution": "720p"
    }
  }),
});
if (!resp.ok) throw new Error(`submit failed: ${resp.status} ${await resp.text()}`);
let task = await resp.json();

// 2) Poll until a terminal state (completed / failed / cancelled).
//    This model is allowed up to 1800s server-side.
const deadline = Date.now() + 1860 * 1000;
while (!["completed", "failed", "cancelled"].includes(task.status)) {
  if (Date.now() > deadline) throw new Error(`still ${task.status} — keep the task_uuid and poll later`);
  await new Promise((r) => setTimeout(r, 3000));
  const poll = await fetch(`https://www.namifusion.com/api/v1/marketplace/run/tasks/${task.task_uuid}`, { headers: HEADERS });
  if (!poll.ok) throw new Error(`poll failed: ${poll.status}`);
  task = await poll.json();
}

console.log(task.status, task.output);

Documentation

Character Swap - Analyze

Detect and track every person in a video before assigning replacement character references.

Character Swap Analyze is the first stage of the two-step Character Swap workflow. It follows people across the input video and returns the obj_id values and track_manifest_url required by the Generate stage. This model does not replace anyone by itself. Keep the analysis result together with the original video and resolution so the next request uses a consistent set of inputs.

Key Features

  • Person detection and tracking: Identifies people in the video and builds object tracks across frames.
  • Selectable previews: Returns an objects list with each person's obj_id, preview, mask, and coverage information.
  • Generate-ready manifest: Produces a track_manifest_url that can be passed directly to Character Swap Generate.
  • Video metadata: Includes width, height, FPS, and frame count in video_info.
  • 480p and 720p analysis: Lets you select the same resolution that will be used for generation.

Technical Specifications

ItemDetails
WorkflowCharacter Swap step 1
Required inputvideo_url
Maximum video length30 seconds
Resolution480p, 720p (default)
Main outputsobjects, track_manifest_url, video_info
Next modelnamifusion/character-swap/generate

Basic Workflow

  1. Send the video URL and selected resolution to namifusion/character-swap/analyze.
  2. Poll the task result endpoint until processing completes.
  3. Review the previews in objects and select the obj_id values to replace.
  4. Pass the same video_url, returned track_manifest_url, and selected IDs to the Generate stage.

Pricing

The existing Marketplace rate is 10 credits per analysis request. This documentation update does not change pricing.

Best Practices

Use a video no longer than 30 seconds in which each person remains clearly visible. Heavy motion blur, long full occlusions, and very small subjects can reduce tracking quality. In Generate, use the same video, resolution, and manifest produced by this Analyze task; do not mix results from separate analyses.