> ## Documentation Index
> Fetch the complete documentation index at: https://docs.eden.art/llms.txt
> Use this file to discover all available pages before exploring further.

# LORA Trainer

> Train a custom model with your images (fast)

## Overview

Train a custom model with your images (fast)

* **Output Type**: lora
* **Base Model**: sdxl
* **Estimated Cost**: 0.2 \* max\_train\_steps credits
* **Handler**: replicate

## Parameters

### Required Parameters

<ParamField body="name" type="string" required>
  Name of the LoRA (this will also be your trigger word)

  * Label: Model Name
</ParamField>

<ParamField body="lora_training_urls" type="array<image>" required>
  Images to train your visual model. (Use at least 5 imgs, 10-20 is even better.)

  * Label: Your training images
</ParamField>

<ParamField body="concept_mode" type="string" required default="style">
  Type of model to train

  * Label: Training Mode
  * Options: `face`, `object`, `style`
</ParamField>

### Optional Parameters

<ParamField body="sd_model_version" type="string" default="sdxl">
  Base Stable Diffusion model to finetune from

  <Tip>
    Almost always, we want to train and SDXL LoRa. Only when we want to make animatediff animations do we need an sd15 lora.
  </Tip>

  * Label: Base SD Model
  * Options: `sdxl`, `sd15`
</ParamField>

<ParamField body="max_train_steps" type="integer" default={300}>
  Number of training steps. Only increase this if you have lots of images (>50) otherwise the model wil overfit and will not look good.

  <Tip>
    This should be left at the default 300, unless the user *specifically* instructs you otherwise. If the base model is SD15, then you should *change* this to 800, again unless the user specifically requests something else.
  </Tip>

  * Label: Training steps
  * Minimum: 100
  * Maximum: 1200
</ParamField>

<ParamField body="resolution" type="integer" default={512}>
  Resolution your images will be resized to for training (512 is great and your generations will still look perfect when rendering at eg 1024)

  <Tip>
    Do not change this unless you are specifically instructed to. Highly recommended to train at 512 for optimal speed and at 768 for best quality.
  </Tip>

  * Label: Resolution
  * Minimum: 512
  * Maximum: 768
</ParamField>

<ParamField body="seed" type="integer" default="random">
  Set random seed for reproducibility. If blank, will be set randomly.

  <Tip>
    You should only set this if you want to start from/copy the seed of a previous image. Unless one is specified, you should leave this blank!
  </Tip>

  * Label: Seed
  * Minimum: 0
  * Maximum: 2147483647
</ParamField>