Hi everyone,

This is an experimental LoRA I created, and I wanted to share both the LoRA and the training data for download. Here's a quick overview of what I did:

Experiment Process:

• I gathered 100 images from MidJourney's Top of August collection. These images were diverse, including various sizes, aspect ratios, and styles.

• I used the MJStyle824 trigger word.

• The images were captioned using Florence 2 Large in Detail_Description mode .

This was purely a curiosity-driven experiment to see if any recognizable style or effects would be captured from such a small and inconsistent dataset. The results were surprisingly noticeable, given the dataset's limitations.

Effects & Performance:

• The effects this LoRA adds are relatively minor, but still more than expected considering the limited and inconsistent data.

• The LoRA works best with higher strength settings in the 0.8 - 1.5 range.

• You can safely push the strength up to 2 for more abstract or non-realistic prompts without encountering significant issues.

Enjoy this quick little experiment and please share, if you get anything interesting :)