---
title: "flux-2-klein-4b-style-lora-trainer"
method: POST
path: "/api/v1/flux-2-klein-4b-style-lora-trainer"
tags: ["Other"]
---

# flux-2-klein-4b-style-lora-trainer

`POST /api/v1/flux-2-klein-4b-style-lora-trainer`

## Request

- Base URL: `https://api.muapi.ai`
- URL: `https://api.muapi.ai/api/v1/flux-2-klein-4b-style-lora-trainer`
- Auth: one of:
  - API key in header `x-api-key`
  - OAuth 2 (client credentials, token URL `https://api.muapi.ai/oauth/token`)

Train custom FLUX.2 [klein] 4B Style LoRA models. Input: dataset zip URL, optional trigger word, steps, learning rate. Output: downloadable safetensors model file and AIR identifier.

## Query parameters

- `webhook` string
- `team_id` integer, nullable

## Headers

- `x-api-key` string
- `x-embed-code` string, nullable
- `x-agent-embed-code` string, nullable
- `x-whitelabel-studio` string, nullable
- `authorization` string, nullable

## Request body

- Flux2Klein4bStyleLoraTrainerRequest
  - `dataset` string, uri, required: URL to ZIP archive containing training images and optional caption text files.
  - `trigger_word` string, nullable: Word or phrase to activate the trained style concept at inference time.
  - `training_steps` integer, nullable: Total number of optimization steps for training.
  - `learning_rate` number, nullable: Learning rate applied at each training update.
  - `webhook_url` string, uri, nullable

## Response `200`

Successful Response

- unknown

## Other responses

- `422`: Validation Error

---

[API](https://skmtc.dev/muapi/apis/muapi-api.md) · [All operations](https://skmtc.dev/muapi/apis/muapi-api/llms.txt) · [OpenAPI document](https://skmtc.dev/muapi/apis/muapi-api/revisions/e4b7374381e5?raw)