---
title: FLUX.2 [klein] 9B KV | Runware Docs
url: https://runware.ai/docs/models/bfl-flux-2-klein-9b-kv
description: KV-cache accelerated image generation and editing for real-time multi-reference workflows
---
# FLUX.2 [klein] 9B KV

![FLUX.2 [klein] 9B KV](https://assets.runware.ai/covers/bfl-flux-2-klein-9b-kv.jpg)

FLUX.2 [klein] 9B KV is a KV-cache optimized variant of the Klein 9B model that caches reference image key-value pairs after the first denoising step, skipping redundant computation on subsequent steps. This delivers up to 2.5x faster inference for multi-reference editing tasks while retaining all capabilities of the standard Klein 9B, including sub-second text-to-image and advanced editing in 4 steps.

- **Status**: live
- **ID**: `runware:400@6`
- Try in Playground
- **Creator**: Black Forest Labs
- **Release Date**: March 20, 2026
- **Capabilities**: Text to Image, Image to Image, Edit, Checkpoint

## Pricing

$0.00078 from, per run · ~3s per request

**Measured runs**

- 1024x1024 · 4 steps: `$0.00078`

**4 example generations**

- [text-to-image](https://runware.ai/docs/models/bfl-flux-2-klein-9b-kv/examples#example-flower-market-thriller-series-poster) · 1024×1024: `$0.00169` (~2s)
- [text-to-image](https://runware.ai/docs/models/bfl-flux-2-klein-9b-kv/examples#example-converted-bank-loft-interior) · 1024×1024: `$0.00169` (~2s)
- [reference-to-image](https://runware.ai/docs/models/bfl-flux-2-klein-9b-kv/examples#example-battery-recycling-scientist-editorial-portrait) · 1280×768: `$0.00247` (~4s)
- [reference-to-image](https://runware.ai/docs/models/bfl-flux-2-klein-9b-kv/examples#example-childrens-mudskipper-science-spread) · 1280×768: `$0.00247` (~4s)

billed by compute time, so a request costs what it took · times vary, measured end to end · [How pricing works](https://runware.ai/docs/platform/pricing)

## Compatibility & Validation

`acceleration` cannot be used with `acceleratorOptions`.

---

`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-klein-9b-kv#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-klein-9b-kv#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-klein-9b-kv#request-outputtype)

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

Image output type.

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

### [outputFormat](https://runware.ai/docs/models/bfl-flux-2-klein-9b-kv#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-klein-9b-kv#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-klein-9b-kv#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/bfl-flux-2-klein-9b-kv#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/bfl-flux-2-klein-9b-kv#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-klein-9b-kv#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-klein-9b-kv#request-safety-checkcontent)

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

Enable or disable content safety checking. Increases total generation time.

### [ttl](https://runware.ai/docs/models/bfl-flux-2-klein-9b-kv#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-klein-9b-kv#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/bfl-flux-2-klein-9b-kv#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/bfl-flux-2-klein-9b-kv#request-acceleration)

- **Type**: `string`
- **Default**: `high`

Optimization level.

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

### [acceleratorOptions](https://runware.ai/docs/models/bfl-flux-2-klein-9b-kv#request-acceleratoroptions)

- **Path**: `acceleratorOptions.cacheEndStep`
- **Type**: `object (10 properties)`

Advanced caching mechanisms to speed up generation.

#### [cacheEndStep](https://runware.ai/docs/models/bfl-flux-2-klein-9b-kv#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/bfl-flux-2-klein-9b-kv#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/bfl-flux-2-klein-9b-kv#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/bfl-flux-2-klein-9b-kv#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/bfl-flux-2-klein-9b-kv#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`.

#### [teaCache](https://runware.ai/docs/models/bfl-flux-2-klein-9b-kv#request-acceleratoroptions-teacache)

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

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

#### [teaCacheDistance](https://runware.ai/docs/models/bfl-flux-2-klein-9b-kv#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/bfl-flux-2-klein-9b-kv#request-acceleratoroptions-dbcache)

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

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

#### [dbCacheThreshold](https://runware.ai/docs/models/bfl-flux-2-klein-9b-kv#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/bfl-flux-2-klein-9b-kv#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.

**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-klein-9b-kv#request-inputs-referenceimages)

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

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-klein-9b-kv#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `runware:400@6`

Identifier of the model to use for generation.

**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-klein-9b-kv#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `1`
- **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/bfl-flux-2-klein-9b-kv#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/bfl-flux-2-klein-9b-kv#request-width)

- **Type**: `integer`
- **Required**: true
- **Min**: `128`
- **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/bfl-flux-2-klein-9b-kv#request-height)

- **Type**: `integer`
- **Required**: true
- **Min**: `128`
- **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/bfl-flux-2-klein-9b-kv#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/bfl-flux-2-klein-9b-kv#request-steps)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `50`
- **Default**: `4`

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)

### [scheduler](https://runware.ai/docs/models/bfl-flux-2-klein-9b-kv#request-scheduler)

- **Type**: `string`

Scheduler to use for the diffusion process.

**Allowed values**: `DDIM` `DDIMScheduler` `DDPMScheduler` `DEISMultistepScheduler` `Default` `DPM++` `DPM++ 2M` `DPM++ 2M Beta` `DPM++ 2M Exponential` `DPM++ 2M Karras` `DPM++ 2M SDE` `DPM++ 2M SDE Beta` `DPM++ 2M SDE Exponential` `DPM++ 2M SDE Karras` `DPM++ 2M SDE Uniform` `DPM++ 2M Uniform` `DPM++ 3M` `DPM++ 3M Beta` `DPM++ 3M Exponential` `DPM++ 3M Karras` `DPM++ 3M SDE Uniform` `DPM++ 3M Uniform` `DPM++ Beta` `DPM++ Exponential` `DPM++ Karras` `DPM++ SDE` `DPM++ SDE Beta` `DPM++ SDE Exponential` `DPM++ SDE Karras` `DPM++ Uniform` `DPM++ Uniform Beta` `DPM++ Uniform Exponential` `DPM++ Uniform Karras` `DPMSolverMultistepInverse` `DPMSolverMultistepScheduler` `DPMSolverSinglestepScheduler` `EDMDPMSolverMultistepScheduler` `EDMEulerScheduler` `Euler` `Euler a` `Euler Beta` `Euler Exponential` `Euler Karras` `EulerAncestralDiscreteScheduler` `EulerDiscreteScheduler` `FlowMatchEulerDiscreteScheduler` `Heun` `HeunDiscreteScheduler` `Heun Karras` `IPNDMScheduler` `IPNDM Uniform` `IPNDM Uniform Beta` `IPNDM Uniform Exponential` `IPNDM Uniform Karras` `KDPM2AncestralDiscreteScheduler` `KDPM2DiscreteScheduler` `LCM` `LCMScheduler` `LMS` `LMSDiscreteScheduler` `LMS Karras` `PNDMScheduler` `TCDScheduler` `UniPC` `UniPC 2M` `UniPC 2M Karras` `UniPC 2M Uniform` `UniPC 3M` `UniPC 3M Karras` `UniPC 3M Uniform` `UniPC Karras` `UniPC Uniform` `UniPC Uniform Beta` `UniPC Uniform Exponential` `UniPC Uniform Karras`

**Learn more** (2 resources):

- [Schedulers](https://runware.ai/docs/learn/schedulers) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [CFGScale](https://runware.ai/docs/models/bfl-flux-2-klein-9b-kv#request-cfgscale)

- **Type**: `float`
- **Min**: `1`
- **Max**: `20`
- **Step**: `0.01`
- **Default**: `3.5`

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/bfl-flux-2-klein-9b-kv#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/bfl-flux-2-klein-9b-kv#request-lora-model)

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

LoRA model identifier.

#### [weight](https://runware.ai/docs/models/bfl-flux-2-klein-9b-kv#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/bfl-flux-2-klein-9b-kv#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-klein-9b-kv#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-klein-9b-kv#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-klein-9b-kv#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-klein-9b-kv#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-klein-9b-kv#request-advancedfeatures-watermark-fontcolor)

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

Text color in hex format.

#### [bgColor](https://runware.ai/docs/models/bfl-flux-2-klein-9b-kv#request-advancedfeatures-watermark-bgcolor)

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

Background color in hex format.

## Response Parameters

### [taskType](https://runware.ai/docs/models/bfl-flux-2-klein-9b-kv#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-klein-9b-kv#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-klein-9b-kv#response-imageuuid)

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

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/bfl-flux-2-klein-9b-kv#response-imageurl)

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

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/bfl-flux-2-klein-9b-kv#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/bfl-flux-2-klein-9b-kv#response-imagedatauri)

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

Data URI of the output image.

### [seed](https://runware.ai/docs/models/bfl-flux-2-klein-9b-kv#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-klein-9b-kv#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/bfl-flux-2-klein-9b-kv#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)

![Flower Market Thriller Series Poster](https://assets.runware.ai/examples/bfl-flux-2-klein-9b-kv/49f4ed50-c395-4902-aee2-07d909d3d0c9.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "8c80cb92-0f55-46b7-bb83-f8a565b2bf80",
  "model": "runware:400@6",
  "positivePrompt": "Finished square streaming-series poster for a prestige crime thriller titled “CUT FLOWERS.” At 4 a.m. inside a cavernous industrial wholesale flower auction hall, a stern middle-aged female auctioneer stands centered in a dark green waterproof apron and work clothes, holding a metal clipboard at her side. She is surrounded by regimented rolling carts overflowing with tightly packed tulips, dahlias and chrysanthemums; the carts create strong converging lines toward her. One cart lies overturned in the foreground, spilling vivid cut flowers across the polished concrete beside a single muddy shoe print, suggesting a mystery without showing violence. Overhead sodium-vapor warehouse lights cast amber pools through cool cyan predawn haze, while saturated magenta, crimson and yellow blossoms punctuate an otherwise restrained charcoal-and-green palette. Low, symmetrical camera angle, deep perspective, crisp realistic materials, subtle condensation on steel carts, cinematic 35mm photography, fine film grain, premium European noir art direction, tense and unsentimental mood. Integrate the exact title CUT FLOWERS in large condensed ivory sans-serif lettering across the upper third, elegant and highly legible, with clear breathing room around it. No other words, logos, billing block, interface elements or decorative border. Cohesive standalone poster artwork, composed specifically for a 1:1 streaming thumbnail with a readable central silhouette.",
  "width": 1024,
  "height": 1024
}
```

---

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

![Converted Bank Loft Interior](https://assets.runware.ai/examples/bfl-flux-2-klein-9b-kv/9e9a9260-547a-450a-b42a-6a3005a93f96.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "9287ed16-dce7-4408-92bc-eb83c577091c",
  "model": "runware:400@6",
  "positivePrompt": "High-end architectural interior photograph of a former 1970s neighborhood bank converted into a ceramic artist's live-work loft. Square composition from the corner of the open living room, showing the original circular stainless-steel vault door repurposed as the entrance to a pantry, a double-height gridded glass facade, exposed board-formed concrete columns, warm birch cabinetry, terracotta tile flooring, and a cobalt-blue modular sofa. A long oak worktable holds a few restrained handmade ceramic vessels. Bright late-morning sunlight casts crisp geometric shadows across the floor; balanced natural exposure, realistic material textures, clean but genuinely inhabited styling. Straight vertical lines, wide-angle architectural lens without distortion, eye-level viewpoint, deep focus, premium real-estate editorial photography, subtle natural color grading, no people, no signage, no visible branding.",
  "negativePrompt": "fantasy architecture, surreal objects, excessive clutter, fisheye distortion, tilted verticals, warped furniture, duplicated objects, people, text, logos, watermark, oversaturated colors, artificial HDR, CGI look",
  "width": 1024,
  "height": 1024
}
```

---

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

![Battery Recycling Scientist Editorial Portrait](https://assets.runware.ai/examples/bfl-flux-2-klein-9b-kv/61340d62-e651-4261-bbd8-c9d236468688.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "b98a27b2-f667-4239-a978-926b4575a25b",
  "model": "runware:400@6",
  "positivePrompt": "Create a finished landscape editorial magazine photograph about advanced battery recycling. Use reference image 1 as the primary subject: preserve the scientist's recognizable facial identity, short natural hair, age, skin tone, clear safety glasses, charcoal coveralls, gloves, and calm direct expression. Use reference image 2 as environmental and visual guidance: preserve the credible facility layout, stainless processing machinery, cobalt-blue tanks, amber tubing, grated walkways, industrial textures, and practical overhead lighting. Recompose the scientist naturally inside that laboratory as if photographed on location, waist-up on the right third of the frame, one gloved hand resting lightly on a safety rail, looking directly into the camera. Show the recycling line receding through the left side of the image, with restrained negative space in the upper left for an editorial headline, but include no text. Sophisticated documentary art direction, cool cobalt and steel palette punctuated by amber tubing, subtle direct-fill flash balanced with existing industrial light, crisp facial detail, realistic skin and fabric, gently controlled background depth, authentic science journalism rather than advertising, 35mm environmental portrait, natural perspective, horizontal magazine-opening composition.",
  "negativePrompt": "text, captions, logos, branding, laboratory signage, futuristic science fiction machinery, fashion glamour, excessive retouching, plastic skin, altered identity, duplicated person, extra people, malformed hands, extra fingers, floating equipment, implausible tubing, extreme wide-angle distortion, heavy cinematic fog, oversaturated colors",
  "width": 1280,
  "height": 768,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/2d503b49-63c0-4371-ab49-4be8c38d4438.jpg",
      "https://assets.runware.ai/assets/inputs/a4a64f65-3115-42ec-9982-12fbf825c76b.jpg"
    ]
  }
}
```

---

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

![Children’s Mudskipper Science Spread](https://assets.runware.ai/examples/bfl-flux-2-klein-9b-kv/4f14f61a-7714-4cfe-a530-4902f2a22793.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "5de25de4-6355-4d0f-ab4e-28f7da54f012",
  "model": "runware:400@6",
  "positivePrompt": "Create a finished landscape educational illustration for an aquarium activity guide aimed at children ages 7–10. Reference image 1 is the primary subject: preserve the mudskipper’s species-accurate silhouette, raised eye shape, blue-speckled brown markings, dorsal fin, pectoral fins and believable proportions. Recompose that animal as the central character climbing over a mangrove prop root at low tide. Reference image 2 is visual guidance only: preserve its layered cut-paper construction, deckled edges, geometric simplification, gentle risograph grain and indigo, coral, mustard, seafoam and cream palette; do not copy its specific plants, animals or layout. Build a wide side-on mangrove mudflat scene with water above and a clear cutaway below the mud. Show three visually legible survival adaptations around the central mudskipper: raised eyes looking above the waterline, strong pectoral fins supporting movement on land, and glossy moist skin indicated by small reflective highlights. Below ground, reveal a curved mud burrow leading to a protected air chamber. Include mangrove roots, tiny fiddler crabs, shell fragments and shallow tide pools at child-friendly scale. Use three small circular inset illustrations connected by clean cream leader lines, with no written labels, so educators can add accompanying copy separately. Keep the science clear and accurate while making the mood curious, cheerful and calm. Balanced 16:9 composition, strong visual hierarchy, generous uncluttered space around the insets, full-bleed standalone artwork, not a book mockup, no border, no interface.",
  "negativePrompt": "photorealistic final rendering, fantasy anatomy, extra fins, fish floating in air, deep ocean reef, tropical postcard aesthetic, muddy indistinct composition, frightening expression, dense text, illegible labels, logos, page mockup, book binding, UI elements",
  "width": 1280,
  "height": 768,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/41ee7aa8-c4bd-4b7f-a51b-8563c20c0879.jpg",
      "https://assets.runware.ai/assets/inputs/02dd9cde-8a0c-4f86-99c2-2759b3babd1e.jpg"
    ]
  }
}
```

---

![Volcanic Shrine Bridal Couture](https://assets.runware.ai/examples/bfl-flux-2-klein-9b-kv/cee0aa0c-cf25-41b2-93e5-0c75552e4021.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "1bbf2426-17f3-45c5-842f-93074f7496ec",
  "referenceImages": [
    "https://assets.runware.ai/assets/inputs/79fa9c73-0d7f-451d-a98f-ab6408b28071.jpg"
  ],
  "model": "runware:400@6",
  "positivePrompt": "Using the reference image as the primary subject guide, transform the figure into an avant-garde bridal look standing on black volcanic stone steps before an ancient mountainside shrine, wind-tossed veil streaming sideways, molten fissures glowing in the distance, drifting ash, lacquered ceremonial gates, dramatic ember-orange rim light against deep charcoal clouds, couture-level fabric detail, elegant silhouette, refined facial features, cinematic composition, ultra-detailed textures, editorial fashion photography, surreal yet believable atmosphere",
  "negativePrompt": "low detail, blurry face, extra limbs, duplicate person, distorted hands, poorly drawn fabric, cartoon, oversaturated skin, flat lighting, cluttered background, text, watermark, frame",
  "width": 1024,
  "height": 1280,
  "seed": 88627,
  "steps": 4,
  "scheduler": "FlowMatchEulerDiscreteScheduler",
  "CFGScale": 3.5
}
```

---

![Clockwork Aviary in Fog](https://assets.runware.ai/examples/bfl-flux-2-klein-9b-kv/19dc7f71-952a-4ae4-a414-678d010a6b2c.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "8b7a2eb2-ea69-4cff-bbdf-c258f74db4ee",
  "model": "runware:400@6",
  "positivePrompt": "An immense Victorian-era glass aviary perched on black seaside cliffs at dawn, filled with intricate brass songbirds, suspended gyroscopes, winding keys, and delicate clockwork vines curling around iron arches. Pale fog pours through cracked panes while warm amber lamps glow inside the structure, contrasting with the cold blue ocean beyond. A lone caretaker in a long cobalt coat stands on a narrow bridge leading into the aviary, tiny against the grand scale. Highly detailed mechanical design, cinematic wide shot, layered depth, elegant symmetry with subtle asymmetry, textured metal, misty atmosphere, refined color grading, crisp focal detail, imaginative realism.",
  "negativePrompt": "low detail, blurry, extra limbs, duplicate subjects, deformed anatomy, text, watermark, logo, oversaturated, flat lighting, cluttered composition",
  "width": 1344,
  "height": 768,
  "seed": 2028,
  "steps": 4,
  "scheduler": "FlowMatchEulerDiscreteScheduler",
  "CFGScale": 3.5
}
```

---

![Salt-Flat Pilgrimage Caravan](https://assets.runware.ai/examples/bfl-flux-2-klein-9b-kv/d29ed2a3-ccb0-499f-88ac-539769a5868d.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "dfb6364a-8b58-4250-ad91-de44acc9e4a9",
  "model": "runware:400@6",
  "positivePrompt": "A sweeping fantasy caravan crossing an endless salt flat at first light, drawing visual cues from the reference images: nomads wearing layered indigo garments with mirrored embroidery and wrapped headpieces, traveling beside tall horned pack beasts with shaggy coats and suspended bundles. Crystalline salt polygons shimmer under low golden light, distant copper mesas rise on the horizon, faint dust ribbons trail behind the caravan, reflective ground creates subtle mirrored silhouettes, cinematic scale, rich environmental storytelling, finely detailed textiles, elegant creature anatomy, atmospheric depth, high realism with painterly finish",
  "negativePrompt": "modern vehicles, city buildings, crowd scene, watermarks, text, logo, blurry details, extra limbs, deformed anatomy, low contrast, oversaturated colors",
  "width": 1344,
  "height": 768,
  "seed": 43362,
  "steps": 4,
  "scheduler": "FlowMatchEulerDiscreteScheduler",
  "CFGScale": 3.5,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/dd8063dd-b76f-4c8c-9225-d562aa4a1291.jpg",
      "https://assets.runware.ai/assets/inputs/9e93a11e-a22b-48f6-94e0-9788ec285e0e.jpg",
      "https://assets.runware.ai/assets/inputs/52b208a8-9808-4af9-a6d4-b3528ecd92e7.jpg"
    ]
  }
}
```

---

![Glacial Cathedral Masked Dancer](https://assets.runware.ai/examples/bfl-flux-2-klein-9b-kv/c1c1971a-e61d-47da-8a44-faeeb2571ad9.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "3f2d5257-6414-4f64-bba4-8b3906a34ebf",
  "model": "runware:400@6",
  "positivePrompt": "Transform the reference subject into a masked ceremonial performer inside a vast glacial cathedral carved from translucent blue ice, towering ribbed arches, suspended crystal banners, frost drifting through shafts of pale gold light, reflective frozen floor, intricate embroidered costume reimagined with pearl, velvet, and faceted ice details, elegant spiraling pose echoing the reference image, cinematic composition, ultra-detailed textures, atmospheric depth, refined anatomy, dramatic scale, fantasy editorial style",
  "negativePrompt": "low detail, blurry, duplicate limbs, extra arms, extra legs, deformed hands, malformed mask, cropped feet, cluttered background, text, watermark, oversaturated, flat lighting",
  "width": 1024,
  "height": 1536,
  "seed": 49352,
  "steps": 4,
  "scheduler": "FlowMatchEulerDiscreteScheduler",
  "CFGScale": 3.5,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/ccd2824e-071b-462a-8d1f-23068812eb9c.jpg"
    ]
  }
}
```