First test with flux concept.
Trained on 35mm photographs from multiple photographers mostly on landscapes, items and buildings. It took on the lighting and esthetics of the dataset pretty well but needs to be pushed into doing grainy pictures if you want those.

Use 35mm Photo, film grain in prompt for best results although it should work without.

Z-Turbo:

First lora for this model, only 896 steps in but a quite a difference already. This was trained using the biggest bucket available in AI-toolkit (from 768 to 1532px).
Use the same dataset, added some more pictures and described the ones I had a lot better to train this one.

Whilst the model is already very capable to do photography, this has to ability to have a bit more contrast and darkness in images.

I keep the value at around 0.8

35mm is triggerword.