This is a training of a public LoRA style (4 seperate training each on 4x A6000).

Experimenting captions vs non-captions. So we will see which yields best results for style training on FLUX.

Generated captions with multi-GPU batch Joycaption app.

I am showing 5 examples of what Joycaption generates on FLUX dev. Left images are the original style images from the dataset.

I used my multi-GPU Joycaption APP (used 8x A6000 for ultra fast captioning)

https://www.patreon.com/posts/110613301

The no caption dataset uses only ohwx 3d render as caption

This is the first training I made with the below dataset

When you pay attention to the grid image above shared, you will see that the dataset is not consistent

It has total 114 images

This training total step count was 500 * 114 / 4 (4x GPU - batch size 1) = 14250

It took like 37 hours on 4x RTX A6000 GPU with slow config - faster config would take like half

There were 2 trainings made with this dataset. Epoch 500 checkpoints are named as below

SECourses_Style_Inconsistent_DATASET_NO_Captions.safetensors SECourses_Style_Inconsistent_DATASET_With_Captions.safetensors

Their checkpoints are saved in below folders

Training-Checkpoints-NO-Captions Training-Checkpoints-With-Captions

Its grid results are shared below

When you pay attention to above image you will see that it has inconsistent results

Hopefully will share trained LoRA on Hugging Face and CivitAI along with full dataset including captions.

I got permission to share dataset but can't be used commercially.

Also I will hopefully share full workflow in the CivitAI and Hugging Face LoRA pages.

So far 450 epochs completed