It's the evolved version of my first 1.5 model. This Lora is for experimental purposes, it's trained on my architectural study images to stir up the architectural discipline and give some critical ideas. I used khoya to train it.

Kubakub_flux1_architecture

In this version, I increased the training data and amount and steps. I haven't tried a lot of prompts yet, but for now, it performs well on physical models. If you don't see any effect, try adding (kubakub:2) or architecture in your prompt.

Files with SHA256: c6305decb8172cc9df7cad9146065aab7e6bc933e2c0733950c78105824b5360