---
title: Krea 2 Raw | Runware Docs
url: https://runware.ai/docs/models/krea-2-raw
description: Base 12B Krea 2 checkpoint for finetuning, post-training, and open-weight text-to-image workflows
---
# Krea 2 Raw

![Krea 2 Raw](https://assets.runware.ai/covers/krea-2-raw.jpg)

Krea 2 Raw is the base release checkpoint in the Krea 2 model family, published as an open-weight 12B text-to-image model before the additional post-training and distillation used for Krea 2 Turbo. Krea describes it as a better fit for finetuning, post-training, and custom domain work than for general inference, making it especially relevant for LoRA training and other open-model customization workflows.

- **Status**: live
- **ID**: `krea:krea@2-raw`
- Try in Playground
- **Creator**: Krea
- **Release Date**: June 22, 2026
- **Zero Data Retention**: Yes
- **Capabilities**: Text to Image, Image to Image, Checkpoint

## Pricing

$0.006 from, per run · ~35s per request

**Measured runs**

- 512×512 · steps 20: `$0.006` (~15s)
- 1024×1024 · steps 20: `$0.0193` (~26s)
- 1024×1024 · steps 40: `$0.0357` (~46s)
- 2048×2048 · steps 20: `$0.0848` (~1m 8s)

**4 example generations**

- [text-to-image](https://runware.ai/docs/models/krea-2-raw/examples#example-water-tower-listening-lounge): `$0.015` (~35s)
- [text-to-image](https://runware.ai/docs/models/krea-2-raw/examples#example-subsea-cable-repair-video-thumbnail): `$0.015` (~52s)
- [text-to-image](https://runware.ai/docs/models/krea-2-raw/examples#example-luxury-watchmaker-oiler-kit-packshot): `$0.015` (~35s)
- [text-to-image](https://runware.ai/docs/models/krea-2-raw/examples#example-night-pollinator-festival-shirt-graphic): `$0.015` (~22s)

billed by compute time, so a request costs what it took · 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/krea-2-raw#request-tasktype)

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

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/krea-2-raw#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/krea-2-raw#request-outputtype)

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

Image output type.

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

### [outputFormat](https://runware.ai/docs/models/krea-2-raw#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/krea-2-raw#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/krea-2-raw#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/krea-2-raw#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/krea-2-raw#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/krea-2-raw#request-safety)

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

Content safety checking configuration for image generation.

#### [checkContent](https://runware.ai/docs/models/krea-2-raw#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/krea-2-raw#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/krea-2-raw#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/krea-2-raw#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.

### [acceleration](https://runware.ai/docs/models/krea-2-raw#request-acceleration)

- **Type**: `string`
- **Default**: `medium`

Optimization level.

**Allowed values**: `none` `low` `medium` `high`

**Inputs**

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

### [referenceImages](https://runware.ai/docs/models/krea-2-raw#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings or objects`
- **Min items**: `1`
- **Max items**: `4`

Style reference images for guiding generation. Each item can be a plain image input (UUID, URL, DataURI, or Base64) or an object with an image and a per-image strength.

**Examples**:

**Shorthand format:** When you don't need to specify a custom strength, you can pass a plain image input directly. It will use the default influence strength.

```json
"referenceImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402"
]
```

**Object format:** When you need to control the exact influence of the reference image, use an object with `image` and `strength`. Positive values guide the output toward the reference; negative values guide away from it.

```json
"referenceImages": [
  {
    "image": "aac49721-1964-481a-ae78-8a4e29b91402",
    "strength": 0.7
  }
]
```

**Multiple images:** You can provide multiple reference images and even mix both formats.

```json
"referenceImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402",
  {
    "image": "3ad204c3-a9de-4963-8a1a-c3911e3afafe",
    "strength": 1.2
  }
]
```

**Format 1: string[]**:

- **Type**: `string`

Image input (UUID, URL, Data URI, or Base64).

**Format 2: object[]**:

#### [image](https://runware.ai/docs/models/krea-2-raw#request-inputs-referenceimages-format-2-image)

- **Path**: `inputs.referenceImages.image`
- **Type**: `string`
- **Required**: true

Image input (UUID, URL, Data URI, or Base64).

#### [strength](https://runware.ai/docs/models/krea-2-raw#request-inputs-referenceimages-format-2-strength)

- **Path**: `inputs.referenceImages.strength`
- **Type**: `float`
- **Min**: `0`
- **Max**: `1`
- **Default**: `0.5`

Influence strength of the reference image on the generated output.

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/krea-2-raw#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `krea:krea@2-raw`

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/krea-2-raw#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **Max**: `10000`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

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

### [negativePrompt](https://runware.ai/docs/models/krea-2-raw#request-negativeprompt)

- **Type**: `string`
- **Min**: `2`
- **Max**: `3000`

Prompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1).

**Learn more** (1 resource):

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

### [width](https://runware.ai/docs/models/krea-2-raw#request-width)

- **Type**: `integer`
- **Required**: true
- **Min**: `64`
- **Max**: `2048`
- **Step**: `16`

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/krea-2-raw#request-height)

- **Type**: `integer`
- **Required**: true
- **Min**: `64`
- **Max**: `2048`
- **Step**: `16`

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/krea-2-raw#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)

### [steps](https://runware.ai/docs/models/krea-2-raw#request-steps)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `100`
- **Default**: `20`

Total number of denoising steps. Higher values generally produce more detailed results but take longer.

**Learn more** (1 resource):

- [Steps](https://runware.ai/docs/learn/steps) (learn)

### [CFGScale](https://runware.ai/docs/models/krea-2-raw#request-cfgscale)

- **Type**: `float`
- **Min**: `0`
- **Max**: `30`
- **Step**: `0.01`
- **Default**: `4.5`

Guidance scale representing how closely the output will resemble the prompt. Higher values produce results more aligned with the prompt.

**Learn more** (1 resource):

- [Cfg Scale](https://runware.ai/docs/learn/cfg-scale) (learn)

### [lora](https://runware.ai/docs/models/krea-2-raw#request-lora)

- **Path**: `lora.model`
- **Type**: `array of objects (2 properties)`
- **Min items**: `1`

With LoRA (Low-Rank Adaptation), you can adapt a model to specific styles or features by emphasizing particular aspects of the data. This technique enhances the quality and relevance of generated content and can be especially useful when the output needs to adhere to a specific artistic style or follow particular guidelines.

Multiple LoRA models can be used simultaneously to achieve different adaptation goals.

**Examples**:

```json
"lora": [
  {
    "model": "<lora-model-air>",
    "weight": 0.8
  }
]
```

**Learn more** (1 resource):

- [Loras](https://runware.ai/docs/learn/loras) (learn)

#### [model](https://runware.ai/docs/models/krea-2-raw#request-lora-model)

- **Path**: `lora.model`
- **Type**: `string`
- **Required**: true

LoRA model identifier.

#### [weight](https://runware.ai/docs/models/krea-2-raw#request-lora-weight)

- **Path**: `lora.weight`
- **Type**: `float`
- **Min**: `-4`
- **Max**: `4`
- **Step**: `0.01`
- **Default**: `1`

Strength of the LoRA influence. A value of 0 means no influence. Higher values increase the influence, and negative values can be used to steer away from the LoRA's style.

**Features**

Standalone addons and post-processing features.

### [watermark](https://runware.ai/docs/models/krea-2-raw#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/krea-2-raw#request-advancedfeatures-watermark-text)

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

Watermark text.

#### [image](https://runware.ai/docs/models/krea-2-raw#request-advancedfeatures-watermark-image)

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

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

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

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

Text color in hex format.

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

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

Background color in hex format.

## Response Parameters

### [taskType](https://runware.ai/docs/models/krea-2-raw#response-tasktype)

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

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/krea-2-raw#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/krea-2-raw#response-imageuuid)

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

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/krea-2-raw#response-imageurl)

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

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/krea-2-raw#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/krea-2-raw#response-imagedatauri)

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

Data URI of the output image.

### [seed](https://runware.ai/docs/models/krea-2-raw#response-seed)

- **Type**: `integer`

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

### [NSFWContent](https://runware.ai/docs/models/krea-2-raw#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/krea-2-raw#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)

![Water Tower Listening Lounge](https://assets.runware.ai/examples/krea-2-raw/ed3044ea-60b2-4615-b6d5-eef17fb75873.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "34ca48e1-4518-4b26-8cea-4c842c2640c8",
  "model": "krea:krea@2-raw",
  "positivePrompt": "High-end architectural interior photograph for a boutique hospitality listing: the circular listening lounge of a converted 1930s concrete water tower. The focal point is a sculptural walnut hi-fi console with a turntable and two large vintage-inspired speakers, centered against the curved board-marked concrete wall. A low rust-colored mohair sectional follows the room’s radius around a round travertine table; one open record sleeve and two handmade ceramic cups suggest quiet use without clutter. Preserve the tower’s industrial character with exposed riveted steel braces, narrow arched window openings, limewashed concrete, and a dark terrazzo floor, balanced by refined custom joinery and tactile upholstery. Rain-darkened city rooftops appear softly through the windows. Cool blue overcast daylight wraps around the curved shell while concealed amber cove lighting grazes the concrete texture, creating a calm, intimate contrast. Symmetrical square composition from standing eye level, 24mm tilt-shift lens, straight verticals, generous sense of volume, realistic spatial proportions, crisp foreground materials, subtle depth toward the windows, natural dynamic range, restrained editorial color grade, photorealistic, finely resolved wood grain, stone pores, brushed metal, woven fabric, and soft window reflections. No people, no signage, no visible branding, no text, no fisheye distortion.",
  "width": 1024,
  "height": 1024
}
```

---

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

![Subsea Cable Repair Video Thumbnail](https://assets.runware.ai/examples/krea-2-raw/3d8e4528-0ddb-4421-8c9b-25e4427da604.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "5bb9aa42-aec8-4041-83df-03e788f4a792",
  "model": "krea:krea@2-raw",
  "positivePrompt": "Square cinematic documentary thumbnail about deep-sea internet infrastructure, grounded in real subsea engineering. A commercial saturation diver in a scuffed yellow diving helmet and heavy black drysuit is the clear focal subject, positioned on the right third and shown from the waist up, gripping an opened armored fiber-optic cable junction with both gloved hands. The cut cable reveals precise concentric layers of tarred jute, steel wire armor, copper tubing, and hair-thin glass fibers catching tiny jewel-like reflections. A powerful helmet lamp throws a warm amber beam across the diver’s scratched faceplate, wet metal fittings, suspended sediment, and drifting marine snow. Behind the diver, the thick cable disappears diagonally into a dark cobalt trench beside a compact hydraulic repair frame, with faint work lights receding into blue-black water. Strong cyan-and-amber color contrast, dramatic readable silhouette, tense but credible industrial atmosphere, crisp foreground detail, realistic underwater falloff, subtle backscatter, volumetric light shafts, pressure-worn materials, documentary photography with premium science-magazine art direction. Leave the upper-left quadrant relatively calm and dark for optional editorial headline placement, but include no text, logos, borders, interface elements, or watermark.",
  "width": 1024,
  "height": 1024
}
```

---

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

![Luxury Watchmaker Oiler Kit Packshot](https://assets.runware.ai/examples/krea-2-raw/70a160fd-a34d-48b5-8fd3-549330c60e70.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "67c42d32-9425-4b48-b25b-f9afea4efd88",
  "model": "krea:krea@2-raw",
  "positivePrompt": "High-end ecommerce studio packshot of a precision watchmaker's micro-oiler kit: five slender oil applicators arranged by height in a compact machined brass stand, each tool featuring a finely knurled anodized-aluminum handle in muted vermilion, saffron, teal, navy, and graphite, hair-thin polished steel shafts, and minute ruby-red jeweled tips. The tallest applicator forms the clear central focal point. Three-quarter front view at tabletop height, centered square composition with generous clean space around the product, every tool fully visible and evenly separated. Set on a seamless matte ultramarine-blue surface that curves into the background. Crisp directional light from upper left creates precise elongated shadows and warm highlights along the brushed brass; a soft cool fill reveals the knurling, tiny machining marks, beveled edges, polished steel reflections, translucent ruby tips, and subtle fingerprints-free satin finish. Focus-stacked commercial product photography, immaculate catalog styling, realistic scale, sharp edge definition, rich but controlled color, premium horology-tool aesthetic. Standalone product image with no hands, no loose parts, no decorative props, no packaging, no logos, no lettering, no watermark.",
  "width": 1024,
  "height": 1024
}
```

---

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

![Night Pollinator Festival Shirt Graphic](https://assets.runware.ai/examples/krea-2-raw/27cb0efa-13f6-4fdb-8ebb-89a1b9c6ab13.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "e19bbe61-5f2c-4784-adce-4407d409c144",
  "model": "krea:krea@2-raw",
  "positivePrompt": "Finished square apparel graphic for a botanical garden’s nocturnal pollinator festival, presented as isolated print artwork rather than a shirt mockup. A large white-lined sphinx moth is the unmistakable central subject, hovering head-on above an open moonflower with its wings fully spread in a strong symmetrical composition. Render the moth with meticulous feathery antennae, powdery wing scales, elegant vein patterns, and a tightly curled proboscis reaching into the flower. Surround it with a circular wreath of moonflower vines, seed pods, trumpet blossoms, and tiny drifting pollen grains. A pale full moon behind the moth creates a crisp halo and dramatic rim lighting; warm coral light glows upward from the flower, illuminating the moth’s underside. Bold hand-drawn arched lettering reads “NIGHT GARDEN” across the top and smaller clean lettering reads “POLLINATOR WEEK 2026” along the bottom. Premium four-color screen-print aesthetic using deep aubergine, pale moon-cream, acidic chartreuse, and luminous coral, with purposeful overprint textures, carved linocut hatching, stippled shadows, slightly imperfect ink edges, and selective solid shapes. Balanced badge-like silhouette, excellent readability from a distance, dense detail concentrated around the focal moth, generous negative space at the corners, vintage natural-history illustration reinterpreted with contemporary gig-poster energy. Print-ready flat artwork on a plain deep aubergine background, no garment, no person, no product mockup, no frame, no extra wording.",
  "width": 1024,
  "height": 1024
}
```