Yes. That's what a LoRa does. It's a way of adding new specific information to an existing model. You would need to upload images of keds from numerous angles, the left and right shoe, the shoes only and the shoe being worn so the ai has a complete image of what the shoe looks like from any angle. Flux is open source so you can run it on local machine with at least 24gb of Ram gpu. Here's a video explaining further.Perhaps a silly question. Can you not train it with existing images?
We use essential cookies to make this site work, and optional cookies to enhance your experience.