Prepare your photo dataset

A LoRA is only as good as the photos you feed it. A short, well-chosen set beats a large, messy one every time.

How many photos

10 to 20 images of the same subject is enough for tendre.AI to learn a face. More photos do not make a better LoRA if they all look alike, variety matters far more than volume.

Vary angles and expressions

Mix close-ups, half-body shots and a few different angles (front, three-quarter, profile). Include a couple of different expressions and, if you can, a couple of different outfits, so the model learns the face and not just one specific photo.

Light and framing

Choose well-lit photos where the face is sharp and clearly visible, ideally not backlit or heavily shadowed. Avoid extreme filters or heavy makeup changes between shots, since they teach the model the wrong thing.

What to leave out

Skip blurry or duplicate shots, photos where the subject is tiny in the frame, and any image showing other people. One clean face per photo keeps the training focused on the right subject.

Ready to train

Once your set matches this, import it in the training panel and start training. See Train a LoRA for the full walkthrough, and Character consistency once your LoRA is trained.