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.
The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.
IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.
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.