The LoRA trained for Flux1 Dev, please read this before use the LoRA:

• Guidance: 3.5

• Sampler/Scheduler: Euler/Beta (feel free to experiment)

• Steps: 20

• Size: 896x1152 (3:4)

• LoRA weight: 0.8 (feel free to experiment)

• Trigger words: pap4pinterest

• Notes: Explain the background, the lighting, the objects to get better result

Anyway, feel free to do some experimentation and I can't wait to see your results in the gallery, please share it :)

How was the dataset captioned?

• I use some short sentence, some long sentence, and some single word.

• I combine chatbot and manual work.

If you have feedback feel free to tell me and I will improve it in the next version.