My 'Model Training' Parammeters for the 'Christmas Model' task of 'Christmas Walkthrough' event


Updated:

Hello!, I've made a LoRA in TensorArt, and i want to share the process

Tutorial for Flux

  1. Have an Idea (Christmas)

  2. Get a Dataset, [min 1024x1024]

    1. Dataset: https://mega.nz/file/DAdHiLwA#-swbYhXvbH2-zMav4JflUDZuERoY-lt_y4RMq7HpzM8

  3. Upload your Dataset

    1. Select Batch Cutting: config for 'vertical, horizontal or squared' depending on your dataset, mine is vertical.

    2. Select Auto Labeling: config for 'florence2, natural lenguage' or enter your captions manually; I'll do both, first auto labeling and then selecting Add Batch Labels to caption my Keywords. Its Important match the 'Keen n Tokens' with the number of Keywords desired.

      1. Keywords: traditional media, christmas parody, fine art, 1940 \(style\)

  4. Config the rest of parammeters (see below)

You're done, start training!

3
0