Bildwerk
screen content blur
RT-DETRv2-S (r18vd, PekingU, Apache-2.0, trained on COCO 2017; pinned ONNX, SHA-256 checked) runs locally with onnxruntime-node on the EXIF-rotated image and, for images with a long side of 900 px or more, additionally on 6 overlapping tiles so small phones are not lost. Detections of the COCO classes tv (TVs and monitors), laptop and cell phone above the score threshold are merged (IoU > 0.5 or 80 % overlap), enlarged by the padding and pixelated, blurred or filled black in the pixels; the.
POST https://bild.halowerk.com/v1/screen-content-blurInputs
| Field | Type | Required | Description |
|---|---|---|---|
| image_base64 | string | No | The image (PNG, JPEG, WebP, GIF, TIFF or AVIF) as base64 or data: URL, at most 10 MB decoded. Give either image_base64 or image_url. |
| image_url | string | No | Public http(s) URL of the image, fetched once (at most 10 MB). Private and local addresses are refused. |
| devices | array | No | Device classes to mask; default all (tv also covers computer monitors). |
| min_score | number | No | Detector score threshold; lower values find more devices and more false boxes. |
| mode | string | No | pixelate = coarse mosaic, blur = strong blur, fill = solid black (strongest). |
| padding | number | No | Box enlargement per side as a fraction of the device size. |
| pixel_blocks | integer | No | Mosaic blocks across the larger box side (pixelate mode). |
| output_format | string | No | Output encoding; "same" keeps JPEG/PNG/WebP and writes PNG for GIF/TIFF and JPEG for AVIF input. |
Show full input schema
{
"type": "object",
"additionalProperties": false,
"properties": {
"image_base64": {
"type": "string",
"minLength": 16,
"maxLength": 14000000,
"description": "The image (PNG, JPEG, WebP, GIF, TIFF or AVIF) as base64 or data: URL, at most 10 MB decoded. Give either image_base64 or image_url."
},
"image_url": {
"type": "string",
"format": "uri",
"maxLength": 2048,
"description": "Public http(s) URL of the image, fetched once (at most 10 MB). Private and local addresses are refused."
},
"devices": {
"type": "array",
"minItems": 1,
"maxItems": 3,
"uniqueItems": true,
"items": {
"type": "string",
"enum": [
"tv",
"laptop",
"cell_phone"
]
},
"description": "Device classes to mask; default all (tv also covers computer monitors)."
},
"min_score": {
"type": "number",
"minimum": 0.25,
"maximum": 0.9,
"default": 0.45,
"description": "Detector score threshold; lower values find more devices and more false boxes."
},
"mode": {
"type": "string",
"enum": [
"pixelate",
"blur",
"fill"
],
"default": "pixelate",
"description": "pixelate = coarse mosaic, blur = strong blur, fill = solid black (strongest)."
},
"padding": {
"type": "number",
"minimum": 0,
"maximum": 0.3,
"default": 0.03,
"description": "Box enlargement per side as a fraction of the device size."
},
"pixel_blocks": {
"type": "integer",
"minimum": 4,
"maximum": 32,
"default": 10,
"description": "Mosaic blocks across the larger box side (pixelate mode)."
},
"output_format": {
"type": "string",
"enum": [
"same",
"jpeg",
"png",
"webp"
],
"default": "same",
"description": "Output encoding; \"same\" keeps JPEG/PNG/WebP and writes PNG for GIF/TIFF and JPEG for AVIF input."
}
}
}Published input example
{
"image_base64": "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",
"mode": "pixelate"
}Result & documentation
Machine-readable documentation of this hub
Source of this page: the published HALOWERK catalog. Updated: 2026-11-17 UTC.
More endpoints in this hub
- Bildwerk0.01 USDC
address plate blur
POSThttps://bild.halowerk.com/v1/address-plate-blurThe photo is read with Tesseract 5.3.4 (German + English, word boxes) at two scales and in sparse-text and block mode; small bright plaques with 1–5 dark characters (typical house-number signs) are additionally cut out and read one by one,
- Bildwerk0.003 USDC
ai disclosure metadata
POSThttps://bild.halowerk.com/v1/ai-disclosure-metadataChecks JPEG, PNG and WebP files for AI disclosure metadata: XMP DigitalSourceType and the IPTC Photo Metadata 2025.1 AI fields, C2PA/JUMBF stores (signatures are not validated), PNG text chunks and EXIF Software/UserComment, and returns a s
- Bildwerk0.008 USDC
animation to video
POSThttps://bild.halowerk.com/v1/animation-to-videoReads frame count, size, loop count and total duration from the file structure, then encodes with ffmpeg 6.1 in a child process under prlimit (no shell, empty environment, only the file protocol): GIF and APNG are demuxed natively, animated