---
title: FLUX.2 [flex] | Runware Docs
url: https://runware.ai/docs/models/bfl-flux-2-flex
description: Configurable FLUX.2 Flex for precise text aligned images
---
# FLUX.2 [flex]

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

FLUX.2 [flex] is a configurable text to image and image editing model built for precise text placement and stable layouts. It exposes sampling and guidance controls and supports up to ten reference images for consistent characters or products across complex compositions.

- **Status**: live
- **ID**: `bfl:6@1`
- Try in Playground
- **Creator**: Black Forest Labs
- **Release Date**: November 25, 2025
- **Zero Data Retention**: Yes
- **Capabilities**: Text to Image, Image to Image, Edit, Checkpoint

## Pricing

$0.06 per output megapixel · ~22s per request

**Rates**

- Output megapixel · per output megapixel: `$0.06`
- Input megapixel · per input megapixel: `$0.06`

**4 example generations**

- [text-to-image](https://runware.ai/docs/models/bfl-flux-2-flex/examples#example-mine-water-heating-explainer) · 1536×1024: `$0.12` (~36s)
- [text-to-image](https://runware.ai/docs/models/bfl-flux-2-flex/examples#example-subsea-cable-repair-feature-illustration) · 1536×1024: `$0.12` (~22s)
- [reference-to-image](https://runware.ai/docs/models/bfl-flux-2-flex/examples#example-polar-logistics-report-cover) · 1024×1536: `$0.24` (~22s)
- [reference-to-image](https://runware.ai/docs/models/bfl-flux-2-flex/examples#example-typefoundry-scratchboard-editorial-portrait) · 1024×1536: `$0.24` (~21s)

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

## Compatibility & Validation

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

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

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

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

Image output type.

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

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

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

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/bfl-flux-2-flex#request-deliverymethod)

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

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

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

### [uploadEndpoint](https://runware.ai/docs/models/bfl-flux-2-flex#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-flex#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-flex#request-safety-checkcontent)

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

Enable or disable content safety checking. Increases total generation time and adds a small charge on top of the generation cost.

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

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/bfl-flux-2-flex#request-numberresults)

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

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Inputs**

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

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

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `10`

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-flex#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `bfl:6@1`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/bfl-flux-2-flex#request-positiveprompt)

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

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

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

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

- **Type**: `integer`
- **Required**: true
- **Min**: `256`
- **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-flex#request-height)

- **Type**: `integer`
- **Required**: true
- **Min**: `256`
- **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-flex#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-flex#request-steps)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `50`
- **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/bfl-flux-2-flex#request-cfgscale)

- **Type**: `float`
- **Min**: `1.5`
- **Max**: `5`
- **Step**: `0.01`
- **Default**: `2.5`

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)

**Features**

Standalone addons and post-processing features.

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

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

Text color in hex format.

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

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

Background color in hex format.

**Provider Settings**

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

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

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

Enable automatic enhancement and expansion of the input prompt.

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

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

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

## Response Parameters

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

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

UUID of the output image.

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

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

URL of the output image.

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

- **Type**: `string`

Base64-encoded image data.

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

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

Data URI of the output image.

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

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

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

![Mine Water Heating Explainer](https://assets.runware.ai/examples/bfl-flux-2-flex/24250898-c0d6-4bd6-9871-e3fbb049bcdf.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "bdf26844-103e-45b0-8ab2-0926f27be993",
  "model": "bfl:6@1",
  "positivePrompt": "Create a finished landscape infographic for a municipal energy authority explaining how heat is recovered from a flooded coal mine and delivered to a neighborhood district heating network. Use a precise editorial cutaway illustration with strong information hierarchy, combining Swiss modernist graphic design, clean vector geometry, subtle screen-printed texture, and technically credible infrastructure details.\n\nAcross the top, place the large exact headline: “HEAT BENEATH OUR FEET”. Directly below it, add the smaller exact subtitle: “How warm mine water becomes low-carbon district heating”. Keep both lines crisp, correctly spelled, and left aligned.\n\nThe main visual should occupy the center and lower two-thirds of the canvas: a wide side-on geological cutaway that transitions from an above-ground former coalfield town into the earth below. Above ground, show a compact row of brick homes, a school, a community center, young street trees, and a small energy center. Below ground, reveal layered sandstone and dark coal seams, old mine galleries, a vertical flooded shaft, groundwater, pipes, and directional flow. Make the underground engineering easy to understand rather than dramatic or fantastical.\n\nExplain the process as one continuous left-to-right numbered sequence with five prominent orange number discs and short, exact labels:\n“1  WARM MINE WATER” beside a blue production pipe descending into the flooded shaft.\n“2  HEAT EXCHANGER” beside a clearly drawn plate heat exchanger inside the energy center.\n“3  HEAT PUMP” beside a compact industrial heat-pump unit that raises the usable temperature.\n“4  DISTRICT HEAT LOOP” beside insulated orange supply pipes branching toward the buildings.\n“5  COOL WATER RETURNS” beside a blue return pipe leading back underground to a separate reinjection point.\n\nUse arrows to make the complete cycle unmistakable. Warm mine water should be shown in cyan rising from the mine; transferred heat should change to vivid safety orange after the heat exchanger; the cooler return route should be dark blue. Clearly keep mine water physically separate from the clean district heating loop. Include a small inset detail near the energy center showing two parallel circuits divided by the heat exchanger, labeled exactly “MINE WATER LOOP” and “CLEAN HEAT LOOP”.\n\nAdd three concise callout boxes along the bottom, each with a simple icon and these exact texts:\n“LOCAL RESOURCE” with “Uses heat already present underground”\n“CLOSED HEAT LOOP” with “Mine water does not enter buildings”\n“YEAR-ROUND SUPPLY” with “Heat pumps raise the temperature as needed”\n\nInclude a compact legend in the lower-right corner with three line samples and exact labels: “Warm mine water”, “District heat supply”, and “Cool return”. Add a small footer note: “Simplified system diagram — not to scale”. Do not add any other headlines, logos, branding, statistics, placeholder copy, lorem ipsum, or stray lettering.\n\nArt direction: deep midnight navy background areas, pale warm sandstone land layers, cyan water, safety-orange heat flow, off-white typography, and muted terracotta buildings. Use bold condensed sans-serif for the headline and a highly legible geometric sans-serif for all labels. Maintain generous margins, a disciplined grid, consistent stroke weights, clean leader lines, and ample negative space. Flat frontal composition with slight axonometric depth only where useful. Crisp vector-like edges, restrained grain, subtle paper texture, excellent small-detail legibility, polished museum-exhibit quality. Even studio-style illumination with no cinematic shadows, no photorealism, no decorative fantasy elements. The result must be one standalone 1536x1024 landscape explainer graphic, not a website, app interface, presentation mockup, or framed poster.",
  "width": 1536,
  "height": 1024,
  "providerSettings": {
    "bfl": {
      "promptUpsampling": true
    }
  }
}
```

---

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

![Subsea Cable Repair Feature Illustration](https://assets.runware.ai/examples/bfl-flux-2-flex/6a743719-d931-44c2-9aee-68de334bac39.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "acfc02bf-149f-4b94-8d36-044cefbce2f6",
  "model": "bfl:6@1",
  "positivePrompt": "Create a finished landscape editorial illustration for a technology magazine feature about emergency undersea internet-cable repair. Use a sophisticated seinen manga and anime-inspired visual language with crisp ink contours, expressive character drawing, cinematic perspective, precise industrial details, selective cel shading, and richly painted atmospheric backgrounds.\n\nShow a cable-repair ship operating at night during rough weather, presented in a dramatic split-level cutaway composition. The upper third reveals the ship’s rain-lashed working deck beneath a deep indigo sky. In the main focal area, a female marine engineer in orange waterproof coveralls, white hard hat, safety harness, and wet gloves braces beside a huge circular cable drum while guiding a thick black fiber-optic cable through yellow deck machinery. Her posture is focused and physically believable rather than heroic posing. Two deck crew members coordinate behind her near a hydraulic winch; include realistic guardrails, pulley assemblies, bundled ropes, warning stripes, steel grating, work lamps, spray, and rain streaking diagonally across the scene.\n\nBelow the ocean surface, reveal a vast dark-blue underwater cross-section occupying roughly half the image. The cable descends through shafts of turquoise work light toward the seabed, where a compact yellow remotely operated vehicle uses articulated manipulator arms to lift the damaged end from a trench. Show accurate-looking thrusters, tether, cameras, sediment clouds, scattered rocks, and small deep-sea fish for scale. A narrow exposed section of the cable should reveal tiny glowing fiber strands in cyan, magenta, and amber, creating a restrained visual metaphor for global data flowing through physical infrastructure.\n\nCompose the image on a strong diagonal from the illuminated ship at upper left through the engineer and cable machinery to the ROV at lower right. Use a slightly elevated wide-angle viewpoint so the deck action and underwater operation read instantly in one coherent scene. Keep the engineer’s face visible in three-quarter profile, lit by a cold cyan monitor glow from one side and a warm amber work lamp from the other. Contrast saturated safety orange and industrial yellow against navy, petrol blue, steel gray, and luminous turquoise. Emphasize wet reflective surfaces, wind-driven spray, deep water haze, suspended particles, and the enormous scale of the ocean.\n\nThe tone is urgent, intelligent, grounded, and technically credible: critical infrastructure maintained by skilled people under difficult conditions. Avoid fantasy technology, giant robots, decorative steampunk elements, comedy, pin-up styling, exaggerated anatomy, chibi proportions, logos, captions, labels, speech bubbles, watermarks, borders, or any written text. Deliver a polished standalone magazine-quality illustration with clean silhouettes, readable visual hierarchy, anatomically correct hands, consistent machinery, and detailed but controlled rendering across the full 3:2 landscape frame.",
  "width": 1536,
  "height": 1024,
  "providerSettings": {
    "bfl": {
      "promptUpsampling": true
    }
  }
}
```

---

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

![Polar Logistics Report Cover](https://assets.runware.ai/examples/bfl-flux-2-flex/2d63c135-a0ad-4442-8307-9d82c8b7f928.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "d9df2bb7-3347-4ae4-bb1c-fffd0d82f537",
  "model": "bfl:6@1",
  "positivePrompt": "Create a finished 2:3 portrait annual operations report cover for a professional Antarctic logistics organization. Treat Reference Image 1 as the original photographic core and visibly outpaint it into the taller portrait canvas: preserve the recognizable orange articulated tracked cargo vehicle, its exact proportions, black track assemblies, cab glazing, roof lights, antennas, tow coupling, white equipment module, camera angle, and existing ice-shelf horizon. Extend the scene naturally far above with a monumental pale overcast polar sky and below with wind-combed snow, shallow track impressions, and subtle blue-gray ice texture. The expansion must feel like one continuous photograph with consistent perspective, grain, weather, and diffuse daylight, not a collage.\n\nIncorporate the field supervisor from Reference Image 2 as a small but clearly readable human figure standing beside the front track of the vehicle. Preserve the supervisor's cobalt insulated suit, reflective silver bands, orange gloves, charcoal balaclava, clear goggles, black boots, body proportions, and recognizable visual details. Match the figure convincingly to the scale, cold ambient light, contact shadows, and wind direction of the vehicle scene.\n\nUse restrained high-end documentary art direction: cold cyan, chalk white, graphite gray, and safety orange; crisp operational realism; austere, capable, calm mood; subtle airborne ice crystals; no dramatic storm, no fantasy elements. Compose the vehicle across the lower-middle third, with the person near it for scale, a large quiet sky above, and clean snow foreground below. Maintain useful negative space without making the image feel empty.\n\nAdd precise editorial typography directly within the image. At upper left, set the exact title “SOUTHBOUND” in large uppercase condensed sans serif lettering, charcoal black. Directly beneath it, set “LOGISTICS REPORT 2026” in smaller uppercase sans serif lettering with wide tracking. At the bottom left, add the small line “ANTARCTIC FIELD OPERATIONS” in uppercase. Keep all text correctly spelled, sharply printed, aligned to one clean left edge, and comfortably inside print-safe margins. No company logo, no additional writing, no border, no mockup, no book shown in a scene. Deliver one full-bleed photographic report cover.",
  "width": 1024,
  "height": 1536,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/b2111c66-6e55-4fca-b7c7-222df067bfe6.jpg",
      "https://assets.runware.ai/assets/inputs/0b73a51e-dfb3-4a12-b9fd-c7fe2db08262.jpg"
    ]
  }
}
```

---

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

![Typefoundry Scratchboard Editorial Portrait](https://assets.runware.ai/examples/bfl-flux-2-flex/7f13e739-ac17-4484-a684-5643e5cacbf8.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "ca73a680-f9e6-462a-9ece-a7accb07e34f",
  "model": "bfl:6@1",
  "positivePrompt": "Create a finished vertical editorial portrait by restyling and combining both reference photographs into one cohesive hand-cut scratchboard illustration for a serious craft and manufacturing magazine. Use reference image 1 as the primary composition and preserve the typefounder’s recognizable facial features, short dark curls, round wire-frame glasses, indigo apron, cream shirt, seated three-quarter posture, hands, and small graver. Keep her expression calm, intelligent, and intensely focused. Integrate the steel letter punch and matching brass matrix from reference image 2 as enlarged foreground objects resting naturally on the near edge of her workbench, preserving their proportions, dark patina, squared forms, beveled edges, and the clearly identifiable uppercase R on the punch end and recessed R in the matrix. The result must feel like a deliberate single scene rather than a collage.\n\nTranslate all photographic detail into an accomplished scratchboard and relief-engraving aesthetic: dense hand-incised white lines cut through velvety black shapes, disciplined cross-hatching, tapered marks, carved highlights, and tactile irregular edges. Use a restrained palette of soot black, warm bone paper, oxidized copper, muted indigo, and one very small vermilion accent on a tool handle. Strong raking light from the upper left should articulate her face, fingers, graver, punch, and matrix while the workshop shelves dissolve into rhythmic engraved shadow. Compose for a 2:3 portrait page: her head in the upper third, working hands near the center, and the punch and matrix prominent but believable in the lower foreground. Include generous quiet negative space around the upper right for editorial flexibility, but place no headline, masthead, caption, border, logo, or decorative lettering there. Preserve only the engraved letter R that belongs physically to the referenced tool. Full-bleed standalone illustration, exacting and intimate mood, sophisticated printmaking texture, clear visual hierarchy, no split panels, no mockup, no photorealistic remnants.",
  "width": 1024,
  "height": 1536,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/2fddcbfe-29f6-487b-9240-1fba05e4c53e.jpg",
      "https://assets.runware.ai/assets/inputs/d90c5419-9cae-47ad-b6fc-18a18c2353c2.jpg"
    ]
  }
}
```