Training a LoRa on any model could be challenging sometimes but in the case of Flux model is easier than SDXL or SD 1.5, especially if you have some guidelines.

Here's my experience creating a "Twisty The Clown" LoRa on-site training feature.

First thing first

Tensor.art Account

Set up an account on Tensor.art and ensure it has a minimum of 300 credits.

Dataset Guidelines

For optimal results, it is advisable to include between 10 o 20 images in your dataset. The majority of these should be close-up photographs, complemented by a few mid-range shots and at least one full-body image. Additionally, incorporating side profile images alongside front-facing ones will enhance the dataset's diversity.

To ensure efficient training and high-quality outcomes, the recommended image size is 512x512 pixels

Here is my dataset that I've used for this LoRa.

Guidelines for Captioning Photos for LoRA

Tensor.art automatically put captions on your images but consider adding:

Unique Trigger Word: Begin each caption with a distinctive trigger word that identifies the dataset.

Also consider this on your captions.

1. Descriptive Tags: Include tags for all elements you wish to vary in the generated images. For instance, if you intend to modify attributes like hair color and length, ensure these are detailed in every photo caption.

2. Consistent Elements: Any aspect not explicitly described and that remains consistent across all photos in the dataset will automatically be associated with the trigger word

Parameter Settings and Likeness Capture

Utilizing a collection of approximately 12 portrait photographs, a highly effective and adaptable likeness LoRA can be developed. The training employs default Flux settings, with modifications to enhance the accuracy.

Here is my Parameter Settings

First select Profesional Mode in the settings