---
title: Kandinsky 5.0 Image Lite | Runware Docs
url: https://runware.ai/docs/models/kandinsky-5-0-image-lite
description: Efficient text-to-image and image-to-image editing model
---
# Kandinsky 5.0 Image Lite

Kandinsky 5.0 Image Lite is an open-source image model that generates high-quality images from text prompts and performs image-to-image edits using a reference image. It blends strong prompt adherence with visual fidelity across diverse visual concepts.

- **ID**: `runware:kandinsky-5.0-image-lite@1`
- **Status**: live
- **Release Date**: November 26, 2025
- **Capabilities**: Text to Image, Image to Image, Image Editing

## Pricing

- **1024x1024**: `$0.0077`

## Compatibility & Validation

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

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `1K (1:1)` | `1024x1024` |
| `1K (~9:20)` | `640x1408` |
| `1K (~20:9)` | `1408x640` |
| `1K (3:5)` | `768x1280` |
| `1K (5:3)` | `1280x768` |
| `1K (7:9)` | `896x1152` |
| `1K (9:7)` | `1152x896` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-tasktype)

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

Identifier for the type of task being performed

### [taskUUID](https://runware.ai/docs/models/kandinsky-5-0-image-lite#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/kandinsky-5-0-image-lite#request-outputtype)

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

Image output type.

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

### [outputFormat](https://runware.ai/docs/models/kandinsky-5-0-image-lite#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/kandinsky-5-0-image-lite#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/kandinsky-5-0-image-lite#request-webhookurl)

- **Type**: `string`
- **Format**: `URI`

Specifies a webhook URL where JSON responses will be sent 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/platform/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-deliverymethod)

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

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns complete results directly in the API response.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

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

### [uploadEndpoint](https://runware.ai/docs/models/kandinsky-5-0-image-lite#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/kandinsky-5-0-image-lite#request-safety)

- **Path**: `safety.checkContent`
- **Type**: `object (2 properties)`

Content safety checking configuration for image generation.

#### [checkContent](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-safety-checkcontent)

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

Enable or disable content safety checking. When enabled, defaults to `fast` mode.

#### [mode](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-safety-mode)

- **Path**: `safety.mode`
- **Type**: `string`
- **Default**: `none`

Safety checking mode for image generation.

**Allowed values**:

- `none` Disables checking.
- `fast` Performs a single check.

### [ttl](https://runware.ai/docs/models/kandinsky-5-0-image-lite#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/kandinsky-5-0-image-lite#request-includecost)

- **Type**: `boolean`
- **Default**: `false`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/kandinsky-5-0-image-lite#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.

### [acceleratorOptions](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-acceleratoroptions)

- **Path**: `acceleratorOptions.cacheEndStep`
- **Type**: `object (12 properties)`

Advanced caching mechanisms to speed up generation.

#### [cacheEndStep](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-acceleratoroptions-cacheendstep)

- **Path**: `acceleratorOptions.cacheEndStep`
- **Type**: `integer`
- **Min**: `1`

Absolute step number to end caching. Must be greater than `cacheStartStep` and less than or equal to `steps`.

#### [cacheEndStepPercentage](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-acceleratoroptions-cacheendsteppercentage)

- **Path**: `acceleratorOptions.cacheEndStepPercentage`
- **Type**: `integer`
- **Min**: `1`
- **Max**: `100`

Percentage of steps to end caching. Alternative to `cacheEndStep`. Must be greater than `cacheStartStepPercentage`.

#### [cacheMaxConsecutiveSteps](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-acceleratoroptions-cachemaxconsecutivesteps)

- **Path**: `acceleratorOptions.cacheMaxConsecutiveSteps`
- **Type**: `integer`
- **Min**: `1`
- **Max**: `5`
- **Default**: `3`

Limits the maximum number of consecutive steps that can use cached computations before forcing a fresh computation.

#### [cacheStartStep](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-acceleratoroptions-cachestartstep)

- **Path**: `acceleratorOptions.cacheStartStep`
- **Type**: `integer`
- **Min**: `0`

Absolute step number to start caching. Must be less than `cacheEndStep`.

#### [cacheStartStepPercentage](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-acceleratoroptions-cachestartsteppercentage)

- **Path**: `acceleratorOptions.cacheStartStepPercentage`
- **Type**: `integer`
- **Min**: `0`
- **Max**: `99`

Percentage of steps to start caching. Alternative to `cacheStartStep`. Must be less than `cacheEndStepPercentage`.

#### [fbCache](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-acceleratoroptions-fbcache)

- **Path**: `acceleratorOptions.fbCache`
- **Type**: `boolean`
- **Default**: `false`

First Block Cache (FBCache) acceleration. Reuses feature block computations across steps.

#### [fbCacheThreshold](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-acceleratoroptions-fbcachethreshold)

- **Path**: `acceleratorOptions.fbCacheThreshold`
- **Type**: `float`
- **Min**: `0`
- **Max**: `1`
- **Step**: `0.01`
- **Default**: `0.25`

Controls the sensitivity threshold for determining when to reuse cached computations. Lower values reuse more aggressively.

#### [teaCache](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-acceleratoroptions-teacache)

- **Path**: `acceleratorOptions.teaCache`
- **Type**: `boolean`
- **Default**: `false`

TeaCache acceleration for transformer-based models. Estimates step differences to skip redundant computations.

#### [teaCacheDistance](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-acceleratoroptions-teacachedistance)

- **Path**: `acceleratorOptions.teaCacheDistance`
- **Type**: `float`
- **Min**: `0`
- **Max**: `1`
- **Step**: `0.01`
- **Default**: `0.5`

Controls the aggressiveness of the TeaCache feature. Lower values prioritize quality, higher values prioritize speed.

#### [dbCache](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-acceleratoroptions-dbcache)

- **Path**: `acceleratorOptions.dbCache`
- **Type**: `boolean`
- **Default**: `false`

DB Cache (CacheDiT) acceleration. Caches and reuses intermediate transformer block outputs to skip redundant computations.

#### [dbCacheThreshold](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-acceleratoroptions-dbcachethreshold)

- **Path**: `acceleratorOptions.dbCacheThreshold`
- **Type**: `float`
- **Min**: `0`
- **Max**: `1`
- **Step**: `0.01`
- **Default**: `0.25`

Controls the sensitivity threshold for DB Cache. Lower values reuse cached blocks more aggressively, higher values prioritize quality.

#### [dbCacheSkipInterval](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-acceleratoroptions-dbcacheskipinterval)

- **Path**: `acceleratorOptions.dbCacheSkipInterval`
- **Type**: `integer`
- **Min**: `1`
- **Default**: `5`

Controls how many steps to skip between cache refreshes. Higher values skip more steps for faster generation at the cost of quality.

**Generation Parameters**

Core parameters for controlling the generated content.

### [model](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `runware:kandinsky-5.0-image-lite@1`

Identifier of the model to use for generation.

**Learn more** (3 resources):

- [Text To Image: Model Selection The Foundation Of Generation](https://runware.ai/docs/guides/text-to-image#model-selection-the-foundation-of-generation) (guide)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/guides/image-inpainting#model-specialized-inpainting-models) (guide)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/guides/image-outpainting#other-critical-parameters) (guide)

### [positivePrompt](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **Max**: `32000`

Text prompt describing elements to include in the generated output.

**Learn more** (2 resources):

- [Text To Image: Prompts Guiding The Generation](https://runware.ai/docs/guides/text-to-image#prompts-guiding-the-generation) (guide)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/guides/image-outpainting#other-critical-parameters) (guide)

### [negativePrompt](https://runware.ai/docs/models/kandinsky-5-0-image-lite#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):

- [Text To Image: Prompts Guiding The Generation](https://runware.ai/docs/guides/text-to-image#prompts-guiding-the-generation) (guide)

### [width](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-width)

- **Type**: `integer`
- **Required**: true
- **Step**: `16`
- **Paired with**: height

Width of the generated media in pixels.

**Learn more** (2 resources):

- [Image To Image: Dimensions Changing Aspect Ratio](https://runware.ai/docs/guides/image-to-image#dimensions-changing-aspect-ratio) (guide)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/guides/image-outpainting#dimensions-critical-for-outpainting) (guide)

### [height](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-height)

- **Type**: `integer`
- **Required**: true
- **Step**: `16`
- **Paired with**: width

Height of the generated media in pixels.

**Learn more** (2 resources):

- [Image To Image: Dimensions Changing Aspect Ratio](https://runware.ai/docs/guides/image-to-image#dimensions-changing-aspect-ratio) (guide)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/guides/image-outpainting#dimensions-critical-for-outpainting) (guide)

### [seed](https://runware.ai/docs/models/kandinsky-5-0-image-lite#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):

- [Text To Image: Seed Controlling Randomness Deterministically](https://runware.ai/docs/guides/text-to-image#seed-controlling-randomness-deterministically) (guide)

### [steps](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-steps)

- **Type**: `integer`
- **Min**: `10`
- **Max**: `50`
- **Default**: `20`

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

**Learn more** (1 resource):

- [Text To Image: Steps Trading Quality For Speed](https://runware.ai/docs/guides/text-to-image#steps-trading-quality-for-speed) (guide)

### [scheduler](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-scheduler)

- **Type**: `string`

Scheduler to use for the diffusion process.

**Allowed values**: `DPM++ 2M Karras` `DPM++ SDE Karras` `DPM++ 2M SDE Exponential` `DPM++ 2M SDE Karras` `Euler` `Euler a` `Euler Trailing` `LCM` `DDIM` `DDPM` `PNDM` `UniPC`

**Learn more** (2 resources):

- [Text To Image: Scheduler The Algorithmic Path To Your Image](https://runware.ai/docs/guides/text-to-image#scheduler-the-algorithmic-path-to-your-image) (guide)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/guides/image-outpainting#other-critical-parameters) (guide)

### [CFGScale](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-cfgscale)

- **Type**: `float`
- **Min**: `2`
- **Max**: `10`
- **Step**: `0.01`
- **Default**: `7`

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

**Learn more** (1 resource):

- [Text To Image: Cfg Scale Balancing Creativity And Control](https://runware.ai/docs/guides/text-to-image#cfg-scale-balancing-creativity-and-control) (guide)

### [lora](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-lora)

- **Path**: `lora.model`
- **Type**: `array of objects (3 properties)`

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):

- [Text To Image: Loras Style And Subject Adapters](https://runware.ai/docs/guides/text-to-image#loras-style-and-subject-adapters) (guide)

#### [model](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-lora-model)

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

LoRA model identifier.

#### [weight](https://runware.ai/docs/models/kandinsky-5-0-image-lite#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.

#### [transformer](https://runware.ai/docs/models/kandinsky-5-0-image-lite#request-lora-transformer)

- **Path**: `lora.transformer`
- **Type**: `string`
- **Default**: `both`

Transformer stages to apply LoRA. Some video models use separate high-noise and low-noise processing stages, and LoRAs can be selectively applied to optimize their effectiveness.

**Allowed values**:

- `high` Apply LoRA only to the high-noise processing stage (coarse structure and early generation steps).
- `low` Apply LoRA only to the low-noise processing stage (fine details and later generation steps).
- `both` Apply LoRA to both stages for full coverage.

## Response Parameters

### [taskType](https://runware.ai/docs/models/kandinsky-5-0-image-lite#response-tasktype)

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

Type of the task.

### [taskUUID](https://runware.ai/docs/models/kandinsky-5-0-image-lite#response-taskuuid)

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

UUID of the task.

### [imageUUID](https://runware.ai/docs/models/kandinsky-5-0-image-lite#response-imageuuid)

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

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/kandinsky-5-0-image-lite#response-imageurl)

- **Type**: `string`
- **Format**: `URI`

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/kandinsky-5-0-image-lite#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/kandinsky-5-0-image-lite#response-imagedatauri)

- **Type**: `string`
- **Format**: `URI`

Data URI of the output image.

### [seed](https://runware.ai/docs/models/kandinsky-5-0-image-lite#response-seed)

- **Type**: `integer`

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

### [NSFWContent](https://runware.ai/docs/models/kandinsky-5-0-image-lite#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/kandinsky-5-0-image-lite#response-cost)

- **Type**: `float`

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

## Examples

### Submerged Marble Ballroom Ruins (Text to Image)

![Submerged Marble Ballroom Ruins](https://assets.runware.ai/examples/kandinsky-5-0-image-lite/38a316f0-1e50-4e3b-b270-cf27cc5cb2e4.jpg)

**Request**:

```json
{
  "taskType": "imageInference",
  "taskUUID": "f05d45ad-e63e-44d8-a247-c2dcc3ab0b94",
  "model": "runware:kandinsky-5.0-image-lite@1",
  "positivePrompt": "An ancient marble ballroom resting deep beneath clear ocean water, grand cracked columns and drifting silk banners, a lone harp anchored to the tiled floor, schools of silver fish winding through shattered chandeliers, rays of sunlight filtering from the surface far above, suspended dust and tiny bubbles, mosaic floor with seashell inlays, overgrown coral crawling across ornate staircases, elegant architecture reclaimed by marine life, cinematic wide shot, richly detailed textures, serene and haunting atmosphere, realistic water caustics, high visual fidelity, painterly realism",
  "negativePrompt": "text, watermark, logo, blurry, low detail, distorted anatomy, extra objects floating in foreground, oversaturated colors, frame, border",
  "width": 1280,
  "height": 768,
  "seed": 18222,
  "steps": 28,
  "scheduler": "DPM++ 2M Karras",
  "CFGScale": 7.5
}
```

**Response**:

```json
{
  "taskType": "imageInference",
  "taskUUID": "f05d45ad-e63e-44d8-a247-c2dcc3ab0b94",
  "imageUUID": "26a8cd3e-834f-4624-890d-92d5d4157386",
  "imageURL": "https://im.runware.ai/image/os/a14d18/ws/2/ii/26a8cd3e-834f-4624-890d-92d5d4157386.jpg",
  "seed": 18222,
  "cost": 0.0102
}
```

---

### Ornate Skywhale Caravan Crossing (Text to Image)

![Ornate Skywhale Caravan Crossing](https://assets.runware.ai/examples/kandinsky-5-0-image-lite/889a27d7-63e0-46f1-bc51-8af6717bb74e.jpg)

**Request**:

```json
{
  "taskType": "imageInference",
  "taskUUID": "4adf9b1d-720a-43d5-a7a4-549f60e0183d",
  "model": "runware:kandinsky-5.0-image-lite@1",
  "positivePrompt": "A vast fantasy sky scene featuring a caravan of enormous gentle skywhales drifting above terraced farmland and winding rivers, each creature fitted with ornate silk canopies, brass lantern chains, hanging cargo baskets, and tiny travelers in colorful layered garments. One lead skywhale carries a miniature garden and wind banners across its back. Below, patchwork fields, stone aqueducts, and distant hilltop villages recede into soft haze. Golden early-morning sunlight, sweeping clouds, cinematic scale, rich atmospheric perspective, highly detailed textures, elegant color harmony, whimsical realism, painterly yet crisp, sense of wonder and serene adventure.",
  "negativePrompt": "underwater, ballroom, ruins, marble hall, futuristic city, cyberpunk, text, watermark, logo, blurry, low detail, deformed anatomy, cropped subject, oversaturated, harsh shadows",
  "width": 1408,
  "height": 640,
  "seed": 64961,
  "steps": 28,
  "scheduler": "DPM++ 2M Karras",
  "CFGScale": 7.5
}
```

**Response**:

```json
{
  "taskType": "imageInference",
  "taskUUID": "4adf9b1d-720a-43d5-a7a4-549f60e0183d",
  "imageUUID": "83b97096-a276-4452-b303-f4ffeba561cb",
  "imageURL": "https://im.runware.ai/image/os/a04d20/ws/2/ii/83b97096-a276-4452-b303-f4ffeba561cb.jpg",
  "seed": 64961,
  "cost": 0.0096
}
```

---

### Submerged Ballroom Ruins Tableau (Text to Image)

![Submerged Ballroom Ruins Tableau](https://assets.runware.ai/examples/kandinsky-5-0-image-lite/aff87441-de5d-4774-b193-0e12a87f0f14.jpg)

**Request**:

```json
{
  "taskType": "imageInference",
  "taskUUID": "212af706-dd0f-4cf9-b2f5-9d92037854d2",
  "model": "runware:kandinsky-5.0-image-lite@1",
  "positivePrompt": "A grand forgotten ballroom resting on the seafloor, seen through clear turquoise water: cracked marble floor, tilted chandeliers draped in seaweed, shoals of silver fish weaving between gilded columns, a full-size cello lying beside a coral-covered staircase, velvet curtains floating gently, scattered pearls and broken masks on the tiles, shafts of sunlight rippling down from the surface, distant arches fading into blue haze, elegant surrealism, cinematic composition, highly detailed textures, refined color harmony, atmospheric depth, realistic caustics, crisp focus",
  "negativePrompt": "text, watermark, logo, blurry, low detail, distorted anatomy, extra limbs, duplicate objects, oversaturated, noisy, flat lighting, frame, border",
  "width": 1152,
  "height": 896,
  "seed": 36203,
  "steps": 28,
  "scheduler": "DPM++ 2M Karras",
  "CFGScale": 7.5
}
```

**Response**:

```json
{
  "taskType": "imageInference",
  "taskUUID": "212af706-dd0f-4cf9-b2f5-9d92037854d2",
  "imageUUID": "94feb8d5-338e-44a4-b801-8a82ac90d3c6",
  "imageURL": "https://im.runware.ai/image/os/a23d05/ws/2/ii/94feb8d5-338e-44a4-b801-8a82ac90d3c6.jpg",
  "seed": 36203,
  "cost": 0.0109
}
```

---

### Volcanic Glass Conservatory Atrium (Text to Image)

![Volcanic Glass Conservatory Atrium](https://assets.runware.ai/examples/kandinsky-5-0-image-lite/2e8babc0-e110-4a2c-b4ce-43a303907343.jpg)

**Request**:

```json
{
  "taskType": "imageInference",
  "taskUUID": "04397a1d-65d2-46a2-b15c-20ad308854cc",
  "model": "runware:kandinsky-5.0-image-lite@1",
  "positivePrompt": "A grand conservatory built from dark volcanic glass and black steel, rising above a steaming geothermal valley at sunrise; enormous curved panes refract warm amber light into prismatic bands across rare tropical plants, suspended walkways, reflecting pools, fern canopies, and mineral terraces. In the center, a circular platform displays giant spiral seed pods and unusual orchids, while distant vents release soft white plumes beyond the structure. Elegant visitors in weatherproof formal attire move through the scene, tiny against the monumental greenhouse architecture. Hyper-detailed environmental design, cinematic depth, crisp botanical textures, subtle atmospheric haze, realistic reflections, rich contrast, polished fantasy realism, ultra coherent composition.",
  "negativePrompt": "underwater, ballroom, marble ruins, blurry, low detail, distorted anatomy, extra limbs, duplicate people, text, watermark, logo, oversaturated, flat lighting, cropped subject",
  "width": 1152,
  "height": 896,
  "seed": 2213,
  "steps": 28,
  "scheduler": "DPM++ 2M Karras",
  "CFGScale": 7.5
}
```

**Response**:

```json
{
  "taskType": "imageInference",
  "taskUUID": "04397a1d-65d2-46a2-b15c-20ad308854cc",
  "imageUUID": "eaffaba0-b142-48fa-8315-e25bdb142d8b",
  "imageURL": "https://im.runware.ai/image/os/a15d18/ws/2/ii/eaffaba0-b142-48fa-8315-e25bdb142d8b.jpg",
  "seed": 2213,
  "cost": 0.0109
}
```