---
title: Riverflow 2.5 Pro | Runware Docs
url: https://runware.ai/docs/models/sourceful-riverflow-2-5-pro
description: Higher-accuracy production image generation and editing for packaging, branding, and commercial design
---
# Riverflow 2.5 Pro

![Riverflow 2.5 Pro](https://assets.runware.ai/covers/sourceful-riverflow-2-5-pro.jpg)

Riverflow 2.5 Pro is the higher-capability variant in Sourceful's Riverflow 2.5 family. It supports both text-to-image and image-to-image workflows and is positioned for commercial visual work that needs stronger output quality, tighter brand control, and more dependable production results across packaging, product imagery, advertising, and design-heavy creative pipelines.

- **Status**: live
- **ID**: `sourceful:riverflow-2.5@pro`
- Try in Playground
- **Creator**: Sourceful
- **Release Date**: June 5, 2026
- **Capabilities**: Text to Image, Image to Image, Edit, Checkpoint, Transparency

## Pricing

$0.235 from, per run · ~2m 34s per request

**Rates** (per run)

- 1K · Low: `$0.235`
- 1K · Medium: `$0.236`
- 1K · High: `$0.245`
- 1K · Extra high: `$0.497`

**4 example generations**

- [text-to-image](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro/examples#example-historic-cemetery-flood-adaptation-visualization) · 1248×832: `$0.179` (~2m 38s)
- [solid-background](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro/examples#example-savory-tomato-cocktail-menu-portrait) · 896×1120: `$0.203` (~2m 1s)
- [transparent-background](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro/examples#example-luna-moth-pastry-menu-cutout) · 1024×1024: `$0.253` (~2m 30s)
- [reference-to-image](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro/examples#example-tidal-aquaculture-operations-icon-set) · 2K: `$0.72` (~3m)

priced per job by the provider, so these are typical rather than exact · times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

`resolution` cannot be used with `width/height`.

---

When `resolution` is provided, `inputs.referenceImages` is required.

---

When `settings.backgroundMode` is `solid`, `settings.backgroundColor` is required.

---

When `settings.backgroundMode` is `transparent`, `outputFormat` is limited to `PNG`, `WEBP`.

---

`width` and `height` must be used together.

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `1K (1:1)` | `1024x1024` |
| `1K (21:9)` | `1456x624` |
| `1K (16:9)` | `1280x720` |
| `1K (3:2)` | `1248x832` |
| `1K (4:3)` | `1152x864` |
| `1K (5:4)` | `1120x896` |
| `1K (4:5)` | `896x1120` |
| `1K (3:4)` | `864x1152` |
| `1K (2:3)` | `832x1248` |
| `1K (9:16)` | `720x1280` |
| `2K (1:1)` | `2048x2048` |
| `2K (21:9)` | `3024x1296` |
| `2K (16:9)` | `2560x1440` |
| `2K (3:2)` | `2496x1664` |
| `2K (4:3)` | `2304x1728` |
| `2K (5:4)` | `2240x1792` |
| `2K (4:5)` | `1792x2240` |
| `2K (3:4)` | `1728x2304` |
| `2K (2:3)` | `1664x2496` |
| `2K (9:16)` | `1440x2560` |
| `4K (1:1)` | `2880x2880` |
| `4K (21:9)` | `3808x1632` |
| `4K (16:9)` | `3840x2160` |
| `4K (3:2)` | `3504x2336` |
| `4K (4:3)` | `3264x2448` |
| `4K (5:4)` | `3200x2560` |
| `4K (4:5)` | `2560x3200` |
| `4K (3:4)` | `2448x3264` |
| `4K (2:3)` | `2336x3504` |
| `4K (9:16)` | `2160x3840` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `imageInference`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Image output type.

**Allowed values**: `URL` `base64Data` `dataURI`

### [outputFormat](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-outputformat)

- **Type**: `string`
- **Required**: conditional — Required when settings.backgroundMode is transparent
- **Default**: `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.

> [!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.

**Allowed values**: `JPG` `PNG` `WEBP`

### [outputQuality](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-outputquality)

- **Type**: `integer`
- **Min**: `20`
- **Max**: `99`
- **Default**: `95`

Compression quality of the output. Higher values preserve quality but increase file size.

### [webhookURL](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-deliverymethod)

- **Type**: `string`
- **Default**: `sync`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-uploadendpoint)

- **Type**: `string`
- **Format**: `uri`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [safety](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-safety)

- **Path**: `safety.checkContent`
- **Type**: `object (1 property)`

Content safety checking configuration for image generation.

#### [checkContent](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-safety-checkcontent)

- **Path**: `safety.checkContent`
- **Type**: `boolean`

Enable or disable content safety checking. Increases total generation time and adds a small charge on top of the generation cost.

### [ttl](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `20`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [referenceImages](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `10`

List of reference images (UUID, URL, Data URI, or Base64).

### [fonts](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-inputs-fonts)

- **Path**: `inputs.fonts`
- **Type**: `array of objects (2 properties)`
- **Max items**: `2`

Font references containing a font URL and the text to render.

#### [text](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-inputs-fonts-text)

- **Path**: `inputs.fonts.text`
- **Type**: `string`
- **Required**: true
- **Min**: `1`

Text to render with this font.

#### [url](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-inputs-fonts-url)

- **Path**: `inputs.fonts.url`
- **Type**: `string`
- **Required**: true
- **Format**: `uri`

Font file URL. Must be ttf, otf, woff, or woff2.

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `sourceful:riverflow-2.5@pro`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **Max**: `24000`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

### [width](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-width)

- **Type**: `integer`
- **Paired with**: height

Width of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [height](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-height)

- **Type**: `integer`
- **Paired with**: width

Height of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [resolution](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-resolution)

- **Type**: `string`
- **Default**: `1K`

Resolution preset for the output. When used with input media, automatically matches the aspect ratio from the input.

**Allowed values**: `1K` `2K` `4K`

**Settings**

Technical parameters to fine-tune the inference process. These must be nested inside the \`settings\` object.

### [backgroundColor](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-settings-backgroundcolor)

- **Path**: `settings.backgroundColor`
- **Type**: `string`

Hex color composited when backgroundMode is solid.

### [backgroundMode](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-settings-backgroundmode)

- **Path**: `settings.backgroundMode`
- **Type**: `string`
- **Default**: `original`

Background handling mode for the final output.

**Allowed values**:

- `original` Keep the original background.
- `transparent` Remove the background for a transparent result.
- `solid` Replace the background with a solid color.

### [enhancePrompt](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-settings-enhanceprompt)

- **Path**: `settings.enhancePrompt`
- **Type**: `boolean`

Enhance the prompt with use-case context before generation.

### [scoringPrompt](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-settings-scoringprompt)

- **Path**: `settings.scoringPrompt`
- **Type**: `string`
- **Min**: `1`

Free-text quality rubric used when scoring candidate outputs.

### [scoringRubric](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-settings-scoringrubric)

- **Path**: `settings.scoringRubric`
- **Type**: `array of objects (8 properties)`
- **Min items**: `1`
- **Max items**: `8`

Controlled scoring dimensions that replace the default sub-score dimensions for the requested flow.

#### [key](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-settings-scoringrubric-key)

- **Path**: `settings.scoringRubric.key`
- **Type**: `string`
- **Required**: true

Unique machine-readable dimension key.

#### [label](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-settings-scoringrubric-label)

- **Path**: `settings.scoringRubric.label`
- **Type**: `string`
- **Required**: true
- **Min**: `1`
- **Max**: `80`

Short human-readable dimension label.

#### [description](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-settings-scoringrubric-description)

- **Path**: `settings.scoringRubric.description`
- **Type**: `string`
- **Required**: true
- **Min**: `1`
- **Max**: `1000`

Judging criteria for this score dimension.

#### [weight](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-settings-scoringrubric-weight)

- **Path**: `settings.scoringRubric.weight`
- **Type**: `float`
- **Required**: true

Scoring weight. Normalized internally, so weights need not sum to 1.

#### [passingScore](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-settings-scoringrubric-passingscore)

- **Path**: `settings.scoringRubric.passingScore`
- **Type**: `float`
- **Min**: `0`
- **Max**: `1`

Minimum score this dimension must reach.

#### [scoreGuidance](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-settings-scoringrubric-scoreguidance)

- **Path**: `settings.scoringRubric.scoreGuidance`
- **Type**: `array of objects (2 properties)`
- **Max items**: `5`

Scoring anchors that define what the normalized scale means.

##### [score](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-settings-scoringrubric-scoreguidance-score)

- **Path**: `settings.scoringRubric.scoreGuidance.score`
- **Type**: `float`
- **Required**: true
- **Min**: `0`
- **Max**: `1`

Normalized score anchor.

##### [description](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-settings-scoringrubric-scoreguidance-description)

- **Path**: `settings.scoringRubric.scoreGuidance.description`
- **Type**: `string`
- **Required**: true
- **Min**: `1`
- **Max**: `500`

What this score anchor means for the judge.

### [thinkingLevel](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-settings-thinkinglevel)

- **Path**: `settings.thinkingLevel`
- **Type**: `string`
- **Default**: `medium`

Controls the depth of internal reasoning the model performs before generating a response.

**Allowed values**: `low` `medium` `high` `xhigh`

**Features**

Standalone addons and post-processing features.

### [watermark](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-advancedfeatures-watermark)

- **Path**: `advancedFeatures.watermark`
- **Type**: `object (6 properties)`

Configuration object for adding watermarks to generated videos. Watermarks can be applied using either text or image content with customizable positioning and appearance. You must provide either `text` or `image` content for the watermark, but not both.

**Text watermark**:

```json
"advancedFeatures": {
  "watermark": {
    "text": "© 2025 Company",
    "displayPosition": "bottom-right",
    "opacity": 0.6,
    "fontColor": "#ffffff",
    "bgColor": "#000000"
  }
}
```

**Image watermark**:

```json
"advancedFeatures": {
  "watermark": {
    "image": "c64351d5-4c59-42f7-95e1-eace013eddab",
    "displayPosition": "top-left",
    "opacity": 0.6
  }
}
```

**Tiled watermark**:

```json
"advancedFeatures": {
  "watermark": {
    "text": "PREVIEW",
    "tiled": true,
    "opacity": 0.4,
    "fontColor": "#cccccc"
  }
}
```

#### [text](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-advancedfeatures-watermark-text)

- **Path**: `advancedFeatures.watermark.text`
- **Type**: `string`
- **Min**: `2`
- **Max**: `32`

Watermark text.

#### [image](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-advancedfeatures-watermark-image)

- **Path**: `advancedFeatures.watermark.image`
- **Type**: `string`

Watermark image (UUID, URL, Data URI, or Base64).

#### [displayPosition](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-advancedfeatures-watermark-displayposition)

- **Path**: `advancedFeatures.watermark.displayPosition`
- **Type**: `string`

Watermark position.

**Allowed values**: `top-left` `top-center` `top-right` `center-left` `center-center` `center-right` `bottom-left` `bottom-center` `bottom-right` `tiled`

#### [opacity](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-advancedfeatures-watermark-opacity)

- **Path**: `advancedFeatures.watermark.opacity`
- **Type**: `float`
- **Min**: `0.1`
- **Max**: `1`
- **Step**: `0.01`

Watermark opacity.

#### [fontColor](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-advancedfeatures-watermark-fontcolor)

- **Path**: `advancedFeatures.watermark.fontColor`
- **Type**: `string`

Text color in hex format.

#### [bgColor](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#request-advancedfeatures-watermark-bgcolor)

- **Path**: `advancedFeatures.watermark.bgColor`
- **Type**: `string`

Background color in hex format.

## Response Parameters

### [taskType](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `imageInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [imageUUID](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#response-imageuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#response-imageurl)

- **Type**: `string`
- **Format**: `uri`

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#response-imagedatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output image.

### [NSFWContent](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/sourceful-riverflow-2-5-pro#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

## Examples

### text-to-image (text-to-image)

![Historic Cemetery Flood Adaptation Visualization](https://assets.runware.ai/examples/sourceful-riverflow-2-5-pro/11fcae29-eb77-4bd1-930e-86c7cbe4eb4c.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "5db4d439-0dfd-4d12-939f-2c515d9ba157",
  "model": "sourceful:riverflow-2.5@pro",
  "positivePrompt": "Create a finished landscape-architecture visualization for a municipal planning presentation about flood adaptation at a historic coastal cemetery. Show one coherent oblique cutaway view across a gently sloping cemetery immediately after rain. The clear subject is a discreet new stormwater landscape woven respectfully among weathered nineteenth-century limestone headstones, mature live oaks, and low meadow grass. A raised permeable gravel path curves through the middle ground, crossing a shallow planted bioswale filled with blue flag iris, soft rush, sedges, and swamp milkweed. Small stone check dams slow the remaining rainwater, while a recessed rain garden collects runoff near the downhill boundary. Keep all interventions understated, dignified, realistic, and visibly accessible without disturbing graves.\n\nAlong the lower foreground edge, reveal a precise sectional cutaway through the ground: permeable path layers, compacted stone base, clean gravel drainage trench, perforated pipe, geotextile, undisturbed soil horizons, carefully preserved tree roots, and a pale blue-gray water table below. Make the relationship between the visible landscape and concealed drainage construction immediately understandable without labels. Include a modest wrought-iron perimeter fence and glimpses of tidal marsh beyond the cemetery, establishing why flood resilience is needed. No workers, machinery, excavated graves, dramatic damage, or funerary activity.\n\nLighting is calm silver-gold late afternoon after a storm, with breaks in the cloud cover, soft directional sunlight on wet stone, restrained reflections in shallow water, and humid coastal atmosphere. Art direction: highly detailed hand-rendered technical illustration combining opaque gouache, transparent watercolor washes, graphite, and colored pencil on warm ivory paper; the compositional clarity of a contemporary landscape-architecture competition drawing with the tactile dignity of a 1930s civic conservation mural. Muted mineral palette of limestone cream, moss green, celadon, iron gray, rain blue, umber, and small accents of iris violet. Accurate plant forms, believable hydrology, nuanced weathering, crisp construction details, restrained human-scale realism, quiet and reassuring mood. Landscape composition at a 3:2 ratio, with the cemetery scene occupying the upper two-thirds and the sectional ground detail integrated naturally across the lower foreground. Standalone illustration only: no title, labels, legends, numbers, logos, borders, presentation panels, interface elements, or mockup context.",
  "width": 1248,
  "height": 832,
  "settings": {
    "enhancePrompt": true,
    "thinkingLevel": "medium"
  }
}
```

---

### reference-to-image (reference-to-image)

![Tidal Aquaculture Operations Icon Set](https://assets.runware.ai/examples/sourceful-riverflow-2-5-pro/d2043c89-1fb8-41d3-a047-538997ac463a.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "41400b97-4796-4c43-9361-5ed30d66a98f",
  "model": "sourceful:riverflow-2.5@pro",
  "positivePrompt": "Create a polished 12-icon visual system for a commercial oyster hatchery and tidal aquaculture operation. Use the first reference image strictly as the subject and equipment reference: accurately interpret the oyster-farming skiff, floating cage, mesh grow-out bag, navigation buoy, juvenile oyster seed, adult oyster shell, grading sieve, sorting basket, water-quality sample bottle, protective glove, tide gauge, and biosecurity wash station. Use the second reference image strictly as the visual-treatment reference: translate its handcrafted ceramic maritime pictograms, cobalt and turquoise glazing, small coral accents, warm cream ground, bold geometric silhouettes, rounded contours, and subtle human irregularity into a coherent modern icon family. Do not copy the objects shown in the treatment reference; apply only its palette, line character, shape language, and tactile glazed finish to the aquaculture subjects from the first reference.\n\nPresent exactly twelve distinct icons in a precise four-column by three-row grid on one square warm-cream artboard. Each icon occupies an equal invisible cell with generous spacing and identical optical scale. Use simplified front or three-quarter views chosen for immediate recognition, consistent heavy stroke weight, rounded line caps, compact silhouettes, and a shared balance of filled and outlined forms. Keep every symbol legible at small sizes while retaining one or two equipment-specific details. Restrict the palette to deep cobalt blue as the primary color, tidepool turquoise as the secondary color, sparing coral orange for functional highlights, and warm cream negative space. Add a very subtle ceramic-glaze texture within the colored shapes, but preserve crisp professional edges suitable for redrawing as vectors. Flat orthographic design, no perspective scene, no shadows between icons, no gradients, no decorative border, no labels, no letters, no numbers, no logo, no mockup, no interface, and no repeated symbols. The final image should read as a finished, cohesive icon-set presentation commissioned for real hatchery operations, combining marine craft heritage with contemporary wayfinding clarity and dependable production consistency. Compose cleanly for a high-resolution 2K square output.",
  "resolution": "2K",
  "settings": {
    "thinkingLevel": "high"
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/1530a7bf-e3c0-4c51-b481-13ebaf8b3b51.jpg",
      "https://assets.runware.ai/assets/inputs/aa255e57-f921-46b6-a95c-3deedeca7bae.jpg"
    ]
  }
}
```

---

### solid-background (solid-background)

![Savory Tomato Cocktail Menu Portrait](https://assets.runware.ai/examples/sourceful-riverflow-2-5-pro/7cad9ef5-7c2e-4cea-9ba3-6794cceae393.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "e413ddd3-6a74-452f-a9f9-1b1f5373d202",
  "model": "sourceful:riverflow-2.5@pro",
  "positivePrompt": "Create a finished high-end menu photograph of one savory clarified tomato cocktail, treated as a sculptural hero subject. A slender hand-blown coupe glass holds a transparent pale-gold tomato-water drink with a faint warm blush, several precise emerald basil-oil droplets on the surface, and one glossy scarlet cherry tomato pierced by a short matte-black cocktail pick resting neatly across the rim. Add a very thin red chili-salt crescent to only one side of the rim. The drink must look cold, pristine, sophisticated, and genuinely appetizing, with delicate condensation and crisp highlights on the glass. Single isolated subject only: no bottle, no second glass, no ingredients scattered around it, no hands, no tableware, no lettering, no logo. Strong recognizable silhouette with generous negative space around the bowl, stem, and foot. Compose vertically for a portrait restaurant-menu feature, glass centered slightly below the optical midpoint and shown completely from rim to base. Three-quarter eye-level product angle, 100mm commercial food-photography look, sharp garnish and rim, controlled depth of field while preserving the full glass silhouette. Hard directional studio light from upper left creates a luminous liquid, jewel-like red and green accents, precise specular highlights, and a compact grounding shadow; subtle rear rim light cleanly separates every edge from the configured solid background. Contemporary editorial art direction combining luxury cocktail photography with clinical botanical precision. Clean uniform background, no visible horizon, no texture, no gradient, no environmental scene. Photorealistic, premium hospitality campaign quality, meticulous glass geometry, realistic refraction, natural condensation, accurate proportions, restrained styling.",
  "width": 896,
  "height": 1120,
  "settings": {
    "backgroundMode": "solid",
    "backgroundColor": "#E8DCC8"
  }
}
```

---

### transparent-background (transparent-background)

![Luna Moth Pastry Menu Cutout](https://assets.runware.ai/examples/sourceful-riverflow-2-5-pro/2d044a06-f02d-47fb-9c22-0bc6642489ea.png)

```json
{
  "taskType": "imageInference",
  "taskUUID": "0d989723-5cda-4e1b-b1ff-7573542e2f2c",
  "outputFormat": "PNG",
  "model": "sourceful:riverflow-2.5@pro",
  "positivePrompt": "Commercial menu photography of one clearly bounded, fully edible luna moth entremet created for an upscale natural-history museum café. The single pastry has a compact pistachio mousse body and two symmetrical pale celadon wafer-paper wings, with delicate cocoa-butter veining, tiny scalloped edges, subtle toasted gradients, and slim dark-chocolate antennae attached securely to the body. Refined patisserie craftsmanship, realistic edible materials, appetizing texture, minute crisp edge detail, no loose crumbs or detached garnish. Centered three-quarter overhead view showing the complete silhouette, generous clear space on every side, entirely in frame. Soft diffused studio lighting with restrained highlights and natural dimensional shading. Photorealistic premium restaurant menu cutout, precise clean edges, isolated on a truly transparent background with alpha transparency. No plate, no utensils, no props, no hands, no text, no logo, no border, no additional food.",
  "width": 1024,
  "height": 1024,
  "settings": {
    "backgroundMode": "transparent"
  }
}
```