---
title: FLUX.2 [klein] 9B Style LoRA Training | Runware Docs
url: https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training
description: Style LoRA training workflow for FLUX.2 [klein] 9B with downloadable safetensors output
---
# FLUX.2 [klein] 9B Style LoRA Training

![FLUX.2 [klein] 9B Style LoRA Training](https://assets.runware.ai/covers/runware-flux-2-klein-9b-style-lora-training.jpg)

FLUX.2 [klein] 9B Style LoRA Training is a Runware training workflow for producing style-focused LoRA adapters on top of the FLUX.2 Klein 9B architecture. It takes a zipped dataset together with a trigger word and training settings, then outputs a LoRA as a safetensors file that can be downloaded or uploaded directly to the platform for immediate use in downstream image generation workflows.

- **Status**: live
- **ID**: `runware:flux-2-klein-9b@style-lora-training`
- Try in Playground
- **Release Date**: July 24, 2026
- **Zero Data Retention**: Yes
- **Capabilities**: Train

## Pricing

$0.00301 per step

[How pricing works](https://runware.ai/docs/models-api/pricing)

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#request-tasktype)

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

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#request-taskuuid)

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

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [webhookURL](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#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)

### [includeCost](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

**Inputs**

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

### [dataset](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#request-inputs-dataset)

- **Path**: `inputs.dataset`
- **Type**: `string`
- **Required**: true
- **File size**: `up to 4 GB`
- **Unzipped size**: `up to 5 GB`
- **Files**: `up to 20000`
- **Images**: `10 to 10000`
- **File size (each)**: `up to 100 MB`

Training dataset as a ZIP file (UUID or URL) containing the training images, each optionally paired with a `.txt` caption file of the same filename.

### [checkpoint](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#request-inputs-checkpoint)

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

AIR of a LoRA previously trained on Runware to resume from. `trainingSteps` runs as additional steps from its final checkpoint. LoRAs trained elsewhere are not supported.

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `runware:flux-2-klein-9b@style-lora-training`

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)

### [importModel](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#request-importmodel)

- **Path**: `importModel.air`
- **Type**: `object (6 properties)`
- **Required**: true

Configuration for the trained model that is uploaded to the platform after training completes.

#### [air](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#request-importmodel-air)

- **Path**: `importModel.air`
- **Type**: `string`
- **Required**: true
- **Min**: `1`

Artificial Intelligence Resource identifier. Format: `provider:model@version`.

#### [heroImageURL](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#request-importmodel-heroimageurl)

- **Path**: `importModel.heroImageURL`
- **Type**: `string`
- **Format**: `uri`

URL of the hero image.

#### [name](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#request-importmodel-name)

- **Path**: `importModel.name`
- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **Max**: `255`

Name of the model.

#### [private](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#request-importmodel-private)

- **Path**: `importModel.private`
- **Type**: `boolean`
- **Default**: `true`

Whether the model should be private.

#### [shortDescription](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#request-importmodel-shortdescription)

- **Path**: `importModel.shortDescription`
- **Type**: `string`

Short description of the model.

#### [version](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#request-importmodel-version)

- **Path**: `importModel.version`
- **Type**: `string`
- **Min**: `1`

Version of the model.

### [learningRate](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#request-learningrate)

- **Type**: `float`
- **Min**: `0.00001`
- **Max**: `0.01`
- **Default**: `0.00005`

Step size applied at each training update. Lower values learn more slowly but can improve stability.

### [trainingSteps](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#request-trainingsteps)

- **Type**: `integer`
- **Min**: `10`
- **Max**: `4000`
- **Default**: `1000`

Total number of optimization steps to run during training.

### [triggerWord](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#request-triggerword)

- **Type**: `string`
- **Min**: `3`
- **Max**: `100`

Word or phrase used to activate the trained concept at inference time.

## Response Parameters

### [taskType](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#response-tasktype)

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

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#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.

### [cost](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#response-cost)

- **Type**: `float`

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

### [air](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#response-air)

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

AIR of the trained model produced by this run. Use it to run inference with the trained model.

### [outputs](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#response-outputs)

- **Path**: `outputs.files`
- **Type**: `object (3 properties)`
- **Required**: true

The trained model produced by the training run.

#### [files](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#response-outputs-files)

- **Path**: `outputs.files`
- **Type**: `array of objects (2 properties)`
- **Required**: true
- **Min items**: `1`

The file or files that make up the trained model.

##### [uuid](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#response-outputs-files-uuid)

- **Path**: `outputs.files.uuid`
- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output file.

##### [url](https://runware.ai/docs/models/runware-flux-2-klein-9b-style-lora-training#response-outputs-files-url)

- **Path**: `outputs.files.url`
- **Type**: `string`
- **Required**: true
- **Format**: `uri`

URL of the output file.