mirror of
https://github.com/snapotter-hq/SnapOtter.git
synced 2026-08-03 07:46:42 +02:00
All 181 docs markdown files translated into 20 languages (apps/docs/<locale>/**). Companion to the i18n code PR; admin-merged because the file count exceeds GitHub's per-PR CI trigger limit. Validated by pnpm i18n:check (all surfaces, 0 stale/missing) and a clean all-locale docs build.
2.5 KiB
2.5 KiB
description, i18n_source_hash, i18n_provenance, i18n_output_hash
| description | i18n_source_hash | i18n_provenance | i18n_output_hash |
|---|---|---|---|
| Deteksi dan koreksi mata merah bertenaga AI yang disebabkan oleh flash kamera. | 647c6ff1ef7c | human | ca509f56b766 |
Red Eye Removal
Deteksi dan koreksi mata merah bertenaga AI yang disebabkan oleh flash kamera.
API Endpoint
POST /api/v1/tools/image/red-eye-removal
Processing: Asinkron (mengembalikan 202, polling /api/v1/jobs/{jobId}/progress untuk status via SSE)
Model bundle: face-detection (200-300 MB)
Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| file | file | Yes | - | Berkas gambar (multipart) |
| sensitivity | number | No | 50 |
Sensitivitas deteksi mata merah (0-100). Nilai lebih tinggi mendeteksi mata merah yang lebih halus |
| strength | number | No | 70 |
Kekuatan koreksi (0-100). Seberapa agresif menetralkan warna merah |
| format | string | No | - | Format output (penimpaan opsional) |
| quality | number | No | 90 |
Kualitas output (1-100) |
Example Request
curl -X POST http://localhost:1349/api/v1/tools/image/red-eye-removal \
-F "file=@flash-photo.jpg" \
-F 'settings={"sensitivity":60,"strength":80}'
Response
Initial Response (202 Accepted)
{
"jobId": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
"async": true
}
Progress (SSE at /api/v1/jobs/{jobId}/progress)
event: progress
data: {"phase":"processing","stage":"Detecting red eyes...","percent":40}
Final Result (via SSE)
{
"phase": "complete",
"percent": 100,
"result": {
"jobId": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
"downloadUrl": "/api/v1/download/{jobId}/flash-photo_redeye_fixed.png",
"originalSize": 280000,
"processedSize": 290000,
"facesDetected": 2,
"eyesCorrected": 4
}
}
Notes
- Membutuhkan model bundle
face-detectionterpasang (200-300 MB). - Pertama mendeteksi wajah, lalu menemukan area mata dalam setiap wajah, dan akhirnya mengidentifikasi serta mengoreksi piksel mata merah.
- Jumlah
facesDetectedmenunjukkan berapa banyak wajah yang ditemukan;eyesCorrectedadalah jumlah total mata individu yang mata merahnya dikoreksi. - Output selalu PNG untuk pelestarian kualitas maksimum.
- Mendukung format input HEIC/HEIF, RAW, TGA, PSD, EXR, dan HDR via dekode otomatis.