Futuristic City illu

After receiving several questions about how my LoRA models work, here’s a quick explanatory guide.

First of all, I always include a trigger word to properly activate the LoRA. If it doesn't seem to activate, keep in mind that the example images I post use the exact same prompt that I used to create the dataset images. So feel free to draw inspiration from the prompt, either in part or in full.

All of my images are generated using checkpoints that I personally like. As such, my LoRA models may not perform as well with other checkpoints.

Also, I never create datasets with multiple viewing angles. So if you’re not satisfied with the angle of a background, I can create a version with a different point of view upon request. The same goes for colors, style, etc.

Finally, I almost always use a strength of 1 for my LoRA models. However, don’t forget that you can adjust this value based on your needs—for example, anywhere between 0.6 and 1.9.