---
title: FLUX.2 [max] | Runware Docs
url: https://runware.ai/docs/models/bfl-flux-2-max
description: The latest state-of-the-art model from Black Forest Labs, generating images grounded in live web information.
---
# FLUX.2 [max]

![FLUX.2 [max]](https://assets.runware.ai/covers/bfl-flux-2-max.jpg)

FLUX.2 [max] is a high-precision text to image and image editing model from Black Forest Labs that generates visuals grounded in real-time information via live web search. It delivers maximum prompt adherence with multi-reference editing and state-of-the-art consistency across identities, objects, and details.

- **Status**: live
- **ID**: `bfl:7@1`
- Try in Playground
- **Creator**: Black Forest Labs
- **Release Date**: December 16, 2025
- **Zero Data Retention**: Yes
- **Capabilities**: Text to Image, Image to Image, Checkpoint

## Pricing

$0.07 from, per output megapixel · ~47s per request

**Rates**

- First megapixel out · per output megapixel: `$0.07`
- Each further megapixel outper output megapixel · beyond 1: `$0.03`
- Input megapixel · per input megapixel: `$0.03`

**4 example generations**

- [text-to-image](https://runware.ai/docs/models/bfl-flux-2-max/examples#example-moa-skeleton-habitat-composite) · 1536×1024: `$0.10` (~34s)
- [text-to-image](https://runware.ai/docs/models/bfl-flux-2-max/examples#example-night-pollinator-field-crew-graphic) · 1536×1024: `$0.10` (~37s)
- [reference-to-image](https://runware.ai/docs/models/bfl-flux-2-max/examples#example-cryogenic-seed-vault-director-portrait) · 1024×1536: `$0.16` (~1m 11s)
- [reference-to-image](https://runware.ai/docs/models/bfl-flux-2-max/examples#example-coastal-sound-festival-poster) · 1024×1536: `$0.16` (~57s)

times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

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

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/bfl-flux-2-max#request-tasktype)

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

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/bfl-flux-2-max#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/bfl-flux-2-max#request-outputtype)

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

Image output type.

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

### [outputFormat](https://runware.ai/docs/models/bfl-flux-2-max#request-outputformat)

- **Type**: `string`
- **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/bfl-flux-2-max#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/bfl-flux-2-max#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/bfl-flux-2-max#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/bfl-flux-2-max#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/bfl-flux-2-max#request-safety)

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

Content safety checking configuration for image generation.

#### [checkContent](https://runware.ai/docs/models/bfl-flux-2-max#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/bfl-flux-2-max#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/bfl-flux-2-max#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/bfl-flux-2-max#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/bfl-flux-2-max#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `8`

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

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/bfl-flux-2-max#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `bfl:7@1`

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/bfl-flux-2-max#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `1`
- **Max**: `32000`

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/bfl-flux-2-max#request-width)

- **Type**: `integer`
- **Min**: `256`
- **Max**: `2048`
- **Step**: `16`
- **Default**: `1024`

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/bfl-flux-2-max#request-height)

- **Type**: `integer`
- **Min**: `256`
- **Max**: `2048`
- **Step**: `16`
- **Default**: `1024`

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)

### [seed](https://runware.ai/docs/models/bfl-flux-2-max#request-seed)

- **Type**: `integer`
- **Min**: `0`
- **Max**: `9223372036854776000`

Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

**Learn more** (1 resource):

- [Seed](https://runware.ai/docs/learn/seed) (learn)

**Features**

Standalone addons and post-processing features.

### [watermark](https://runware.ai/docs/models/bfl-flux-2-max#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/bfl-flux-2-max#request-advancedfeatures-watermark-text)

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

Watermark text.

#### [image](https://runware.ai/docs/models/bfl-flux-2-max#request-advancedfeatures-watermark-image)

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

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

#### [displayPosition](https://runware.ai/docs/models/bfl-flux-2-max#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/bfl-flux-2-max#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/bfl-flux-2-max#request-advancedfeatures-watermark-fontcolor)

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

Text color in hex format.

#### [bgColor](https://runware.ai/docs/models/bfl-flux-2-max#request-advancedfeatures-watermark-bgcolor)

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

Background color in hex format.

**Provider Settings**

Parameters specific to this model provider. These must be nested inside the \`providerSettings.bfl\` object.

### [promptUpsampling](https://runware.ai/docs/models/bfl-flux-2-max#request-providersettings-bfl-promptupsampling)

- **Path**: `providerSettings.bfl.promptUpsampling`
- **Type**: `boolean`

Enable automatic enhancement and expansion of the input prompt.

### [safetyTolerance](https://runware.ai/docs/models/bfl-flux-2-max#request-providersettings-bfl-safetytolerance)

- **Path**: `providerSettings.bfl.safetyTolerance`
- **Type**: `integer`
- **Min**: `0`
- **Max**: `5`
- **Default**: `2`

Tolerance level for content moderation. Lower values are stricter; higher values are more permissive.

## Response Parameters

### [taskType](https://runware.ai/docs/models/bfl-flux-2-max#response-tasktype)

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

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/bfl-flux-2-max#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/bfl-flux-2-max#response-imageuuid)

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

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/bfl-flux-2-max#response-imageurl)

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

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/bfl-flux-2-max#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/bfl-flux-2-max#response-imagedatauri)

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

Data URI of the output image.

### [seed](https://runware.ai/docs/models/bfl-flux-2-max#response-seed)

- **Type**: `integer`

The seed used for generation. If none was provided, shows the randomly generated seed.

### [NSFWContent](https://runware.ai/docs/models/bfl-flux-2-max#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/bfl-flux-2-max#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)

![Moa Skeleton Habitat Composite](https://assets.runware.ai/examples/bfl-flux-2-max/ed84da31-ead1-4cc0-bbdf-69368d8d01a6.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "f769868d-58a8-40f9-a789-a71accf4a4d6",
  "model": "bfl:7@1",
  "positivePrompt": "Create a finished, photorealistic museum background-replacement composite featuring one complete articulated South Island giant moa skeleton as the clear foreground subject. Present the skeleton in left-facing side profile, nearly full height, mounted on a minimal matte-black conservation armature with a low dark plinth. Preserve intricate cutout-quality detail around every rib, vertebra, toe bone, beak edge, and narrow gap in the skeleton; clean natural edges with no halos or accidental background fragments. Replace the original neutral specimen-photo background with a richly reconstructed prehuman New Zealand South Island temperate rainforest: silver beech trunks, tree ferns, mossy fallen logs, damp leaf litter, pale lichen, fine mist, and layered deep-green foliage receding into atmospheric distance. No modern objects, no people, no living moa, no visible museum interior.\n\nMake the replacement environment feel scientifically plausible and cinematic without becoming fantasy. Soft overcast dawn light filters from the upper left through the canopy, producing cool green ambient light and a restrained warm rim along the weathered ivory bones. Match the lighting direction and color spill across the skeleton, armature, and habitat. Add a convincing contact shadow beneath the plinth, subtle reflected green light on lower bones, mild humid haze behind the subject, and realistic depth of field while keeping the entire skeleton sharply legible. Landscape composition with the moa occupying the central-left two-thirds of the frame and layered forest extending to the right, suitable for a premium museum exhibition panel. Naturalistic palette of fern green, charcoal, damp umber, muted bone ivory, and touches of misty blue-gray. High-end natural-history photography, precise anatomy, refined conservation-documentation clarity, seamless professional compositing, visually rich but educational, no captions, labels, logos, borders, or typography.",
  "width": 1536,
  "height": 1024,
  "providerSettings": {
    "bfl": {
      "promptUpsampling": true
    }
  }
}
```

---

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

![Night Pollinator Field Crew Graphic](https://assets.runware.ai/examples/bfl-flux-2-max/b828bcd0-002b-4da7-8fb8-5046a3ae5f29.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "a525e36b-63d3-489e-ab08-cd0b3da655b3",
  "model": "bfl:7@1",
  "positivePrompt": "Create a finished landscape apparel graphic for the back of a field crew T-shirt commemorating a nocturnal citizen-science pollinator survey in the Sonoran Desert. Show one enormous white-lined sphinx moth in precise dorsal view, wings fully spread and centered, rendered as an intricate vintage scientific scratchboard engraving. Surround it with an arched wreath of blooming sacred datura, desert marigold, agave stalks, and tiny airborne pollen grains. Behind the moth, place a large low desert moon crossed by sparse horizontal cloud bands; below it, add small silhouettes of saguaro cactus, distant basin-and-range mountains, and a subtle sweep of topographic contour lines. Integrate tiny field-journal details—coordinate ticks, specimen registration marks, a crescent moon phase sequence, and restrained star symbols—without making the design feel cluttered.\n\nTypography is a deliberate part of the merchandise design. Across the top, set the exact words “MIDNIGHT POLLINATOR SURVEY” in bold condensed uppercase lettering that curves gently over the moon. Across the bottom, set the exact words “SONORAN DESERT FIELD CREW · 2026” in smaller sturdy uppercase lettering. Keep all text highly legible, correctly spelled, and fully contained inside the composition. Add a tiny ribbon beneath the moth reading exactly “OBSERVE · RECORD · PROTECT”.\n\nArt direction: rugged 1970s natural-history field guide meets contemporary outdoor-workwear graphics; hand-inked linocut and scratchboard character, crisp carved lines, dense ornamental detail, bold symmetrical silhouette, authentic screen-print texture, slightly imperfect ink edges. Use a strict five-ink palette of warm bone, burnt orange, dusty turquoise, chartreuse, and pale lavender on a flat deep midnight-navy background. No gradients, no photorealism, no glossy effects, no garment, no model, no product mockup, no frame, and no extra wording. Make the complete design read clearly from a distance while rewarding close inspection. Centered horizontal composition with generous negative space around every edge, isolated as one production-ready shirt-back graphic in a 3:2 landscape canvas.",
  "width": 1536,
  "height": 1024,
  "providerSettings": {
    "bfl": {
      "promptUpsampling": true
    }
  }
}
```

---

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

![Cryogenic Seed Vault Director Portrait](https://assets.runware.ai/examples/bfl-flux-2-max/8bb6bfff-227b-448b-a656-0f8bedd77878.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "fdc5e7a8-80ea-438f-b198-215ae00ccdb3",
  "model": "bfl:7@1",
  "positivePrompt": "Create a finished professional environmental portrait for the annual report and press kit of an international crop biodiversity institute. Use reference image 1 as the strict identity reference: preserve the woman’s recognizable facial structure, proportions, complexion, dark brown eyes, smile lines, silver-streaked black hair, age, and composed demeanor. She is the institute’s cryogenic seed vault director, photographed with quiet authority and approachability. Use reference image 2 to establish the cold-storage setting, vertical composition, architectural perspective, restrained documentary style, and mixed cool-cyan and soft warm lighting.\n\nShow her from mid-torso upward at eye level, standing slightly left of center while the seed bank corridor recedes behind her. She faces the camera with relaxed shoulders and a direct, steady gaze, wearing a tailored pale stone laboratory coat over a dark teal merino turtleneck. Include simple clean coat details and no visible logos, badges, lettering, or institutional branding. Her clothing should feel practical and senior rather than theatrical. Keep her hands mostly outside the crop.\n\nLight her face with a broad, soft, warm key from camera left that echoes the maintenance lamp in reference image 2, balanced by cool ambient fill from the corridor. Maintain believable color interaction on skin, hair, and clothing. The background should remain clearly identifiable as a modern seed conservation facility while falling gently out of focus; retain the stainless doors, insulated walls, orderly shelving, overhead strips, and strong receding lines from the second reference. Natural skin pores, fine facial lines, individual hair strands, realistic fabric weave, accurate anatomy, and subtle catchlights. Premium editorial corporate photography, 85mm portrait-lens character, moderate shallow depth of field, clean tonal separation, understated cyan, stone, charcoal, and muted teal palette. Calm, exacting, future-focused mood. No glamour retouching, no exaggerated smile, no frozen breath, no frost on the subject, no protective goggles, no dramatic science-fiction elements, no text, no watermark, and no border. Compose specifically for a 1024x1536 vertical image with comfortable space above the head and a publication-ready crop.",
  "width": 1024,
  "height": 1536,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/8f691b01-1133-4579-96b4-a64496bd0b1a.jpg",
      "https://assets.runware.ai/assets/inputs/1b9ca7be-90dd-4a4b-a938-1be3faf9597d.jpg"
    ]
  }
}
```

---

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

![Coastal Sound Festival Poster](https://assets.runware.ai/examples/bfl-flux-2-max/2e020b7e-28bb-4701-9fc8-3badfbc829f3.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "c8e31232-d787-4a67-b030-c837005dc216",
  "model": "bfl:7@1",
  "positivePrompt": "Create a finished 2:3 portrait concert poster for an experimental coastal sound festival. Use reference image 1 to preserve the recognizable identities, facial features, hairstyles, black performance clothing, body proportions, and specific instruments of all three musicians. Use reference image 2 to preserve the distinctive decommissioned foghorn station, its twin circular horn mouths, rugged headland, concrete architecture, cliffs, mist, and dramatic low-angle vertical composition. Integrate the trio naturally into the foreground of that location as the featured performers, not as pasted cutouts.\n\nArt direction: sophisticated limited-edition screen-printed cultural poster combining bold mid-century maritime graphics with contemporary editorial design. Reduce the coastal scene into crisp layered shapes, tactile ink coverage, coarse halftone shadows, subtle paper grain, and slight two-color registration offsets. The giant foghorn mouths form powerful concentric circles behind the musicians, visually echoing drums and sound waves. Wind catches coats and loose hair; sea mist sweeps diagonally across the lower cliffs. Strong hierarchy, generous negative space, dynamic but disciplined geometry. Restrained palette of uncoated warm ivory paper, deep midnight navy, oxidized sea-green, and vivid signal vermilion. Windswept, elemental, intelligent, and culturally credible rather than whimsical. Keep faces legible and faithful to reference 1 while translating the overall image into premium screen-print illustration.\n\nInclude clear, correctly spelled poster typography as an intentional part of the design. At the top, large condensed uppercase title on separate lines: “FOG SIGNAL”. Directly beneath it: “ORKNEY SOUND ART WEEKEND”. In the lower information block, typeset exactly: “18–20 OCTOBER 2026” and “THE OLD FOGHORN STATION · NORTH HEAD”. Add a compact lineup line: “LOW TIDE TRIO · MARA VENN · FIELD STATIC · BRASS WEATHER”. Use bold condensed grotesk lettering for the title and clean Swiss-style sans serif for details. Ensure all text is readable, properly aligned, and contained within safe poster margins. No additional words, logos, sponsor marks, mockup frame, wall, hands, interface, or surrounding environment; output one standalone print-ready poster image.",
  "width": 1024,
  "height": 1536,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/d0908623-ef55-441f-b97c-0f8aa5d01912.jpg",
      "https://assets.runware.ai/assets/inputs/9eaf5586-bdcd-433c-a1ed-ed73e2f8130b.jpg"
    ]
  }
}
```