Docs

Running a model

SourcefulText to image

Sourceful Riverflow 2.5 Pro

Higher-accuracy production image generation and editing for packaging, branding, and commercial design

POSTauray-serverless/sourceful/riverflow-2-5-pro
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 text-to-image · Scope image:write (or external:write on an older key) · Price Credits per call: 22 for resolution=1K, settings.thinkingLevel=low; resolution=1K, settings.thinkingLevel=medium; 41.4167 for resolution=1K, settings.thinkingLevel=xhigh; 60 for resolution=1K, settings.thinkingLevel=high; resolution=2K, settings.thinkingLevel=low; resolution=2K, settings.thinkingLevel=medium; resolution=2K, settings.thinkingLevel=high. 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
inputsobjectno—
inputs.referenceImagesstring[]no—List of reference images (an http(s) URL; upload a local file first and send its read URL). Documented range: 1 to 10.
inputs.fontsobject[]no—
inputs.fonts[].textstringno—Text to render with this font. Documented range: 1 or more characters.
inputs.fonts[].urlstringno—Font file URL. Must be ttf, otf, woff, or woff2. A URL.
positivePromptstringyes—Text prompt describing elements to include in the generated output. Documented range: 2 to 24,000 characters.
widthintegerno1024Width of the generated media in pixels.
heightintegerno1024Height of the generated media in pixels.
resolutionstringno"1K"Resolution preset for the output. When used with input media, automatically matches the aspect ratio from the input. One of "1K", "2K", "4K".
settingsobjectno—
settings.backgroundColorstringno—Hex color composited when backgroundMode is solid.
settings.backgroundModestringno"original"Background handling mode for the final output. One of "original", "transparent", "solid".
settings.enhancePromptbooleanno—Enhance the prompt with use-case context before generation.
settings.scoringPromptstringno—Free-text quality rubric used when scoring candidate outputs. Documented range: 1 or more characters.
settings.scoringRubricobject[]no—
settings.scoringRubric[].keystringno—Unique machine-readable dimension key.
settings.scoringRubric[].labelstringno—Short human-readable dimension label. Documented range: 1 to 80 characters.
settings.scoringRubric[].descriptionstringno—Judging criteria for this score dimension. Documented range: 1 to 1,000 characters.
settings.scoringRubric[].weightnumberno—Scoring weight. Normalized internally, so weights need not sum to 1.
settings.scoringRubric[].passingScorenumberno—Minimum score this dimension must reach. Documented range: 0 to 1.
settings.scoringRubric[].scoreGuidanceobject[]no—
settings.scoringRubric[].scoreGuidance[].scorenumberno—Normalized score anchor. Documented range: 0 to 1.
settings.scoringRubric[].scoreGuidance[].descriptionstringno—What this score anchor means for the judge. Documented range: 1 to 500 characters.
settings.thinkingLevelstringno"medium"Controls the depth of internal reasoning the model performs before generating a response. One of "low", "medium", "high", "xhigh".
outputTypestringno"URL"Image output type. One of "URL".
outputFormatstringno"JPG"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 "JPG", "PNG", "WEBP".
outputQualityintegerno95Compression quality of the output. Higher values preserve quality but increase file size. Documented range: 20 to 99.
safetyobjectno—
safety.checkContentbooleanno—Enable or disable content safety checking. Increases total generation time. Always on: a false is sent as true.
advancedFeaturesobjectno—
advancedFeatures.watermarkobjectno—
advancedFeatures.watermark.textstringno—Watermark text. Documented range: 2 to 32 characters.
advancedFeatures.watermark.imagestringno—Watermark image (an http(s) URL; upload a local file first and send its read URL). A URL.
advancedFeatures.watermark.displayPositionstringno—Watermark position. One of "top-left", "top-center", "top-right", "center-left", "center-center", "center-right", "bottom-left", "bottom-center", "bottom-right", "tiled".
advancedFeatures.watermark.opacitynumberno—Watermark opacity. Documented range: 0.1 to 1.
advancedFeatures.watermark.fontColorstringno—Text color in hex format.
advancedFeatures.watermark.bgColorstringno—Background color in hex format.
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.

  • Send height whenever width is sent. Send width whenever height is sent.
  • Do not send resolution together with width or height.
  • When width is sent or height is sent, width and height must be one of these: 1K (1:1): width 1024, height 1024; 1K (21:9): width 1456, height 624; 1K (16:9): width 1280, height 720; 1K (3:2): width 1248, height 832; 1K (4:3): width 1152, height 864; 1K (5:4): width 1120, height 896; 1K (4:5): width 896, height 1120; 1K (3:4): width 864, height 1152; 1K (2:3): width 832, height 1248; 1K (9:16): width 720, height 1280; 2K (1:1): width 2048, height 2048; 2K (21:9): width 3024, height 1296; and 18 more (30 in all).
  • When settings.backgroundMode is "solid", settings.backgroundColor is required.
  • When settings.backgroundMode is "transparent", outputFormat is required and must be one of "PNG", "WEBP".
  • When resolution is sent, inputs.referenceImages is required.
  • inputs.fonts must hold at most 2 items. In every item of inputs.fonts: inputs.fonts[].url and inputs.fonts[].text are required.
  • settings.scoringRubric must hold 1 to 8 items. In every item of settings.scoringRubric: settings.scoringRubric[].key, settings.scoringRubric[].label, settings.scoringRubric[].description and settings.scoringRubric[].weight are required. In every item of settings.scoringRubric: settings.scoringRubric[].scoreGuidance must hold at most 5 items. In every item of settings.scoringRubric: in every item of settings.scoringRubric[].scoreGuidance: settings.scoringRubric[].scoreGuidance[].score and settings.scoringRubric[].scoreGuidance[].description are required.
  • When advancedFeatures.watermark is sent: send exactly one of advancedFeatures.watermark.text or advancedFeatures.watermark.image.

#Example

curl -X POST https://queue.auray.run/auray-serverless/sourceful/riverflow-2-5-pro \
  -H "Authorization: Bearer $AURAY_API_KEY" \
  -H "content-type: application/json" \
  -d '{
  "positivePrompt": "a brass orrery on a walnut desk, morning light from a window to the left"
}'

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