Docs

Running a model

Topaz LabsVideo to video

Topaz Labs Proteus

General-purpose video enhancement for cleaner detail, stronger face recovery, and more consistent upscaling

POSTauray-serverless/topazlabs/proteus-4
openapi.jsonllms.txt

One of Auray's catalogue models: the same key, the same credits, the same job lifecycle as every other address.

Its request shape is published below. Whether it runs right now is GET /v1/catalogue's word, with no key needed: its addresses say connected for an address that runs, and a submit to any other is refused before anything is charged — described answers 501 model_not_connected, paused 503 model_disabled.

Category video-to-video · Scope video:write (or external:write on an older key) · Price Credits per megapixel (counted as width*height): 2.4114. From 2.0736 to 67.1089 megapixels a request. A request that sends inputs.video is refused before any charge: it has no price on this model. Quoted when you submit, at the most the request can cost; the charge settles to what the job cost and never above the quote. The submit's answer carries the quote as credits_quoted, and credits_charged says what has been taken.

#Input

FieldTypeRequiredDefaultDescription
widthintegeryes1920Width of the generated media in pixels. Acts as an envelope: the source aspect ratio is preserved, so the output can come back narrower, and the value must exceed a fifth of the source width. Documented range: 16 to 8,192.
heightintegeryes1080Height of the generated media in pixels. Acts as an envelope: the source aspect ratio is preserved, so the output can come back shorter, and the value must exceed a fifth of the source height. Documented range: 16 to 8,192.
fpsnumberno—Frames per second for video generation. Defaults to the source frame rate, which is also the lower bound, so a lower value is rejected. Documented range: 1 to 120.
settingsobjectno—
settings.enhancementobjectno—
settings.enhancement.blurnumberno—Amount of sharpness applied. Documented range: -1 to 1.
settings.enhancement.compressionnumberno—Strength of compression recovery. Documented range: -1 to 1.
settings.enhancement.detailsnumberno—Amount of detail reconstruction. Documented range: -1 to 1.
settings.enhancement.grainnumberno—Adds grain after model processing. Documented range: 0 to 0.1.
settings.enhancement.grainSizenumberno—Size of the generated grain. Documented range: 0 to 5.
settings.enhancement.halonumberno—Amount of halo reduction. Documented range: -1 to 1.
settings.enhancement.modestringno—How the tuning weights are applied. One of "auto", "relative", "manual".
settings.enhancement.noisenumberno—Amount of noise reduction. Documented range: -1 to 1.
settings.enhancement.preblurnumberno—Anti-aliasing and deblurring strength. Documented range: -1 to 1.
settings.enhancement.prenoisenumberno—Adds noise to the input to reduce over-smoothing. Documented range: 0 to 0.1.
settings.enhancement.recoverOriginalDetailnumberno—Reintroduces source details into the output video. Documented range: 0 to 1.
settings.fieldOrderstringno—Field order for interlaced sources. One of "topFirst", "bottomFirst", "auto".
settings.focusFixLevelstringno—Downscales the input for stronger correction of blurred subjects. One of "none", "normal", "strong".
settings.videoTypestringno—Frame or field type of the source video. One of "progressive", "interlaced", "progressiveInterlaced".
outputQualityintegerno95Compression quality of the output. Higher values preserve quality but increase file size. Documented range: 20 to 99.
outputTypestringno"URL"Video output type. One of "URL".
outputFormatstringno"MP4"Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities. - `JPG`: Best for photorealistic images with smaller file sizes (no transparency). - `PNG`: Lossless compression, supports high quality and transparency (alpha channel). - `WEBP`: Modern format providing superior compression and transparency support. - `MP4`: Widely supported video container (H.264), recommended for general use. - `WEBM`: Optimized for web delivery. - `MOV`: QuickTime format, common in professional workflows (Apple ecosystem). - `GIF`: Animated image format (no audio), suitable for short loops or previews. - `MP3`: Compressed audio, smaller file size. - `WAV`: Uncompressed, high-quality audio. - `FLAC`: Lossless compression. - `OGG`: Open-source compressed audio format (Vorbis codec). - `SVG`: Scalable Vector Graphics. - `TIFF`: High-quality output supporting layers. - `GLB`: Binary glTF format for 3D models, including geometry, textures, and PBR materials. > [!NOTE] > **Transparency**: If you are using features like background removal or LayerDiffuse that require transparency, you must select a format that supports an alpha channel (e.g., `PNG`, `WEBP`, `TIFF`). `JPG` does not support transparency. One of "MP4", "WEBM", "MOV".
inputsobjectyes—
inputs.videostringyes—Video input (an http(s) URL; upload a local file first and send its read URL). A URL.
idempotency_keystringno—Your own name for this request. Send the same one twice and the second call is answered with the first request rather than charged again. Idempotency-Key: as a header is accepted as an alias — that is the spelling a retrying proxy replays, and the one to use when running a model on auray.run, where a request that outlives its connection is answered 504 and recovered by replay. Omit it and the platform mints one. 1 to 64 characters.

#Rules

Across fields, as the model's documentation states them. Each is judged before anything is charged — warned with a Deprecation header until enforcement starts — and listed as JSON Schema under x-auray-rules in the openapi.json.

  • When settings.fieldOrder is sent, settings.videoType is required and must be one of "interlaced", "progressiveInterlaced".
  • When settings.enhancement.compression is sent, settings.enhancement.details is sent, settings.enhancement.prenoise is sent, settings.enhancement.noise is sent, settings.enhancement.halo is sent, settings.enhancement.preblur is sent, settings.enhancement.blur is sent, settings.enhancement.grain is sent, settings.enhancement.grainSize is sent or settings.enhancement.recoverOriginalDetail is sent, settings.enhancement.mode is required and must be one of "relative", "manual".

#Example

curl -X POST https://queue.auray.run/auray-serverless/topazlabs/proteus-4 \
  -H "Authorization: Bearer $AURAY_API_KEY" \
  -H "content-type: application/json" \
  -d '{
  "width": 1920,
  "height": 1080,
  "inputs": {
    "video": "https://v3b.auray.media/examples/samples/coffee-pour.mp4"
  }
}'

The same body on https://auray.run runs synchronously and answers the result — unless it usually takes longer than a run may hold its connection, which is refused 400 model_not_synchronous before anything is charged. Options — ?webhook=, ?wait=, priority and timeout headers — are on Submit a request.

#Machine contracts

  • openapi.json — this page as an OpenAPI 3.1 document, public.
  • llms.txt — the same, written for an agent.

Start typing to search every page of the documentation.

Up arrow Down arrow to moveEnter to openEscape to close