---
title: UNI-1 Max | Runware Docs
url: https://runware.ai/docs/models/luma-uni-1-max
description: Higher-quality unified image model for premium generation and precision editing
---
# UNI-1 Max

![UNI-1 Max](https://assets.runware.ai/covers/luma-uni-1-max.jpg)

UNI-1 Max is the quality-first variant in Luma's UNI-1 image family for both image creation and precision image editing. It uses the same API shape and capability set as UNI-1, but is tuned for higher-quality output when detail, polish, and final-image quality matter more than using the default variant.

- **Status**: live
- **ID**: `luma:uni@1-max`
- Try in Playground
- **Creator**: Luma
- **Release Date**: May 5, 2026
- **Capabilities**: Text to Image, Image to Image, Checkpoint

## Pricing

$0.10 per run · ~2m 57s per request

**Rates**

- 2K · per run: `$0.10`
- Input image · per input image: `$0.003`

**4 example generations**

- [text-to-image](https://runware.ai/docs/models/luma-uni-1-max/examples#example-adaptive-commuter-rainwear-lookbook) · 2784×1504: `$0.10` (~3m 42s)
- [text-to-image](https://runware.ai/docs/models/luma-uni-1-max/examples#example-big-boy-locomotive-cutaway-plate) · 2784×1504: `$0.10` (~2m 45s)
- [reference-to-image](https://runware.ai/docs/models/luma-uni-1-max/examples#example-tidal-energy-manga-cover-expansion) · 1696×2464: `$0.106` (~2m 26s)
- [image-to-image](https://runware.ai/docs/models/luma-uni-1-max/examples#example-vieques-bioluminescent-bay-campaign) · 2048×2048: `$0.109` (~3m 8s)

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

## Compatibility & Validation

When `inputs.seedImage` is provided, `settings.style` cannot be used.

---

When `inputs.seedImage` is provided, `settings.search` cannot be used.

---

When `inputs.seedImage` is provided, `inputs.referenceImages` is limited to 8 items.

---

When `settings.style` is `manga`, dimensions are limited to `1696×2464`, `1504×2784`, `1440×2912` or `1248×3360`.

---

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

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `3K (~3:1)` | `3360x1248` |
| `3K (~2:1)` | `2912x1440` |
| `3K (~16:9)` | `2784x1504` |
| `3K (~3:2)` | `2464x1696` |
| `3K (1:1)` | `2048x2048` |
| `3K (~2:3)` | `1696x2464` |
| `3K (~9:16)` | `1504x2784` |
| `3K (~1:2)` | `1440x2912` |
| `3K (~1:3)` | `1248x3360` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/luma-uni-1-max#request-tasktype)

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

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/luma-uni-1-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/luma-uni-1-max#request-outputtype)

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

Image output type.

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

### [outputFormat](https://runware.ai/docs/models/luma-uni-1-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/luma-uni-1-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/luma-uni-1-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/luma-uni-1-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/luma-uni-1-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/luma-uni-1-max#request-safety)

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

Content safety checking configuration for image generation.

#### [checkContent](https://runware.ai/docs/models/luma-uni-1-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/luma-uni-1-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/luma-uni-1-max#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/luma-uni-1-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.

### [seedImage](https://runware.ai/docs/models/luma-uni-1-max#request-inputs-seedimage)

- **Path**: `inputs.seedImage`
- **Type**: `string`

Image used as a starting point for the generation (UUID, URL, Data URI, or Base64).

**Learn more** (3 resources):

- [Image To Image: Seed Image The Foundation](https://runware.ai/docs/learn/image-to-image#seed-image-the-foundation) (learn)
- [Image Inpainting: Seed And Mask Image The Foundation](https://runware.ai/docs/learn/image-inpainting#seed-and-mask-image-the-foundation) (learn)
- [Image Outpainting: Seed Image The Starting Point](https://runware.ai/docs/learn/image-outpainting#seed-image-the-starting-point) (learn)

### [referenceImages](https://runware.ai/docs/models/luma-uni-1-max#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `9`

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/luma-uni-1-max#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `luma:uni@1-max`

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/luma-uni-1-max#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **Max**: `6000`

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/luma-uni-1-max#request-width)

- **Type**: `integer`
- **Required**: conditional — Required when settings.style is manga
- **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/luma-uni-1-max#request-height)

- **Type**: `integer`
- **Required**: conditional — Required when settings.style is manga
- **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)

**Settings**

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

### [search](https://runware.ai/docs/models/luma-uni-1-max#request-settings-search)

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

When enabled, the model searches the web for visual references before generating. This improves accuracy for prompts that reference real-world subjects, landmarks, or products.

### [style](https://runware.ai/docs/models/luma-uni-1-max#request-settings-style)

- **Path**: `settings.style`
- **Type**: `string`
- **Default**: `auto`

Applies a style preset to the generation.

**Allowed values**:

- `auto` Model selects the best style for the prompt.
- `manga` Manga/anime aesthetic with ink outlines and screentone shading.

**Features**

Standalone addons and post-processing features.

### [watermark](https://runware.ai/docs/models/luma-uni-1-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/luma-uni-1-max#request-advancedfeatures-watermark-text)

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

Watermark text.

#### [image](https://runware.ai/docs/models/luma-uni-1-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/luma-uni-1-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/luma-uni-1-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/luma-uni-1-max#request-advancedfeatures-watermark-fontcolor)

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

Text color in hex format.

#### [bgColor](https://runware.ai/docs/models/luma-uni-1-max#request-advancedfeatures-watermark-bgcolor)

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

Background color in hex format.

## Response Parameters

### [taskType](https://runware.ai/docs/models/luma-uni-1-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/luma-uni-1-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/luma-uni-1-max#response-imageuuid)

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

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/luma-uni-1-max#response-imageurl)

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

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/luma-uni-1-max#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/luma-uni-1-max#response-imagedatauri)

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

Data URI of the output image.

### [NSFWContent](https://runware.ai/docs/models/luma-uni-1-max#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/luma-uni-1-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)

![Adaptive Commuter Rainwear Lookbook](https://assets.runware.ai/examples/luma-uni-1-max/136e2ff0-a090-4e22-b32e-398b0334e56d.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "9b0f3db3-4a7e-41ca-bd6c-4103f0f16670",
  "model": "luma:uni@1-max",
  "positivePrompt": "High-end fashion lookbook photograph for an adaptive commuter rainwear collection, photographed outside the architecturally accurate Rotterdam Centraal station in the Netherlands. Three adult models form a clean staggered lineup beneath the station’s dramatic angular stainless-steel roof: a wheelchair user in a cropped cobalt waterproof shell with a longer seated back, magnetic storm flap, articulated sleeves and matching charcoal trousers; a standing model with a forearm crutch wearing a matte aubergine trench with asymmetric easy-access closures; and a standing model in a compact acid-yellow packable rain cape over tailored slate commuter wear. Diverse casting, natural confidence, calm neutral expressions. Show every outfit clearly from head to toe, with realistic garment construction, seams, fasteners, fabric texture and functional adaptive details. Wide landscape composition with generous negative space, straight architectural lines and the station facade clearly recognizable but subordinate to the clothing. Cool overcast daylight after rain, soft directional highlights on wet pavement and brushed metal, restrained cobalt, aubergine, acid yellow, graphite and silver palette. Precise contemporary European catalog art direction, crisp editorial photography, eye-level camera, 50mm lens character, moderate depth of field, polished but believable skin and fabric, no dramatic action. One finished standalone image, no collage, no inset detail frames, no captions, no logos, no added typography, no borders.",
  "width": 2784,
  "height": 1504,
  "settings": {
    "search": true,
    "style": "auto"
  }
}
```

---

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

![Big Boy Locomotive Cutaway Plate](https://assets.runware.ai/examples/luma-uni-1-max/28527cad-be9c-4e45-915c-088e3b91606b.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "caed9178-e540-4545-8ad1-68a1f810fc42",
  "model": "luma:uni@1-max",
  "positivePrompt": "Create a finished panoramic technical cutaway illustration for a railway museum exhibition about Union Pacific Big Boy No. 4014. Show the complete locomotive and its tender in a precise left-facing side elevation, centered and spanning nearly the full width with comfortable margins. Preserve the recognizable real-world proportions and construction of this specific restored locomotive: 4-8-8-4 wheel arrangement, articulated front engine, two sets of eight driving wheels, accurate side rods and valve gear, long boiler, smokebox, firebox, cab, and large tender. Retain historically accurate UNION PACIFIC and 4014 markings where they appear on the actual locomotive.\n\nUse selective cutaway sections to reveal the boiler tubes, steam dome, regulator path, cylinders, firebox, combustion chamber, cab controls, coal and water compartments, while keeping the exterior silhouette immediately legible. Apply restrained functional color coding inside the machinery: oxide orange for fire and hot gases, muted teal for water, pale blue-gray for steam, and brass accents for valves; exterior surfaces remain graphite black and warm steel. Render components with crisp mechanical detail, convincing material texture, subtle sectional hatching, and clean diagrammatic separation. No floating parts, speculative machinery, decorative scenery, people, labels, captions, numbered callouts, title block, border, or poster mockup. Background is flat warm ivory with a faint grounded shadow beneath the wheels. Contemporary museum-science art direction combining archival engineering plates, precise digital gouache, and elegant editorial infographics; authoritative, educational, uncluttered, and suitable as the image centerpiece of a large interpretive wall panel.",
  "width": 2784,
  "height": 1504,
  "settings": {
    "search": true,
    "style": "auto"
  }
}
```

---

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

![Tidal Energy Manga Cover Expansion](https://assets.runware.ai/examples/luma-uni-1-max/8bd21069-cc31-4d9d-8eb9-143c64c044a0.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "3e6be435-12b3-48c2-b0eb-61047a11f1be",
  "model": "luma:uni@1-max",
  "positivePrompt": "Create a finished 1696x2464 portrait manga cover illustration by expanding the widescreen scene in Reference 1 into a much taller composition. Treat Reference 1 as the source image to preserve rather than a loose thematic suggestion: retain the technician’s exact facial identity, short blunt black bob with the single white forelock, amber eyes, freckles, proportions, safety-orange cropped jacket, navy waterproof overalls, gloves, clipped white hard hat, torque wrench, crouched working pose, and the central relationship between her body and the turbine housing. Keep this recognizable action near the visual center of the portrait frame.\n\nOutpaint substantial new scene content above and below the original widescreen composition. Above her, reveal the immense vertical interior of the tidal barrage: receding steel gantries, ladders, suspended cables, dripping beams, narrow skylights, and a high strip of cold daylight reflecting from the sea outside. Below her platform, extend into a deep turbine chamber with descending service stairs, foaming seawater, submerged structural ribs, schools of tiny silver fish, and the lower arc of the machinery disappearing into dark teal water. Use the added vertical architecture to emphasize scale and make the technician feel capable but small within a monumental renewable-energy facility.\n\nUse Reference 2 as the strict design reference for the tidal turbine and engineering details. Preserve its open-ring silhouette, six broad curved blades, segmented cobalt housing, orange maintenance locks, circular inspection hatches, grated rails, hydraulic lines, bolt patterns, barnacles, and salt-stained wet surfaces. Integrate those components naturally into the expanded environment without changing their functional construction.\n\nPremium serialized seinen manga artwork for a marine engineering outreach graphic novel: assured black ink contours, intricate mechanical draftsmanship, selective screentone, controlled speed-line accents around dripping water and turbine motion, cinematic perspective, and expressive but anatomically credible character drawing. Restrained palette of cobalt blue, deep navy, oxidized seafoam green, safety orange, cool gray, and white highlights. Moody, industrious, optimistic atmosphere after a storm. Strong portrait cover hierarchy with quieter open space in the upper section for later editorial titling, but render no words, logos, symbols, border, or typography. One clean standalone cover image, not a book mockup.",
  "width": 1696,
  "height": 2464,
  "settings": {
    "style": "manga"
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/e4dc6fe3-6c4d-4d76-bbc7-1f7143e793e0.jpg",
      "https://assets.runware.ai/assets/inputs/df224051-142a-498d-b6ed-77278b2e8041.jpg"
    ]
  }
}
```

---

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

![Vieques Bioluminescent Bay Campaign](https://assets.runware.ai/examples/luma-uni-1-max/c4943fbb-751d-4f76-bbdf-74743b0fe2ca.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "acd8208e-922c-4acb-8608-1f0a1d203000",
  "model": "luma:uni@1-max",
  "positivePrompt": "Create premium destination-campaign photography for a Vieques, Puerto Rico tourism board, using the seed image as the compositional foundation. Preserve the recognizable curved mangrove shoreline, distant hill contours, centered transparent kayak, diagonal paddle, paddler's seated pose, camera viewpoint, and overall depth arrangement from the seed. Substantially transform the daytime scene into a moonless nighttime bioluminescent kayaking experience in Mosquito Bay. The traveler's paddle stroke should ignite a broad, physically believable trail of blue-green dinoflagellate light: countless fine luminous particles, brighter turbulence around the blade and kayak hull, delicate glowing droplets suspended near the paddle, and a tapering wake behind the boat. Use the first reference image to guide the granular character and realistic intensity of the bioluminescence, never making it look like neon paint or fantasy magic. Use the second reference for the authentic mangrove silhouettes, humid nocturnal atmosphere, restrained stars, and deep indigo sky. Keep the traveler natural and anonymous, seen from behind in practical dark excursion clothing and a life vest, with anatomically correct hands and a plausible kayaking posture. Reveal subtle edges of the transparent kayak through the glow beneath it. Art direction: sophisticated eco-adventure tourism photography, immersive and serene rather than extreme, inky navy and black surroundings contrasted with concentrated turquoise and blue-green light. Cinematic low-light exposure with crisp focal detail on the traveler, paddle, and luminous wake, softer mangroves in the distance, realistic reflections, controlled highlights, gentle atmospheric haze, and polished editorial color grading. Square composition with strong visual flow from the lower foreground wake toward the distant center; leave calm dark negative space in the upper sky for optional campaign layout, but include no lettering, logos, borders, signage, interface elements, or watermark. The final result must read as a credible, high-end photograph of a bookable bioluminescent-bay excursion, not an illustration or composite.",
  "width": 2048,
  "height": 2048,
  "inputs": {
    "seedImage": "https://assets.runware.ai/assets/inputs/e51e8f2e-22ed-412d-b895-51678bcb0faf.jpg",
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/8b0f7cae-20e9-481f-8dd8-b27b684a1ed3.jpg",
      "https://assets.runware.ai/assets/inputs/2f398769-b34c-4eb5-bb39-3c4a4db44c9b.jpg"
    ]
  }
}
```