Train Style Model

Fine-tune a reusable brand, style, or character model (a LoRA) from a small set of reference images, then generate on-brand imagery from any prompt. Use when the user says "train a model on our brand style", "make a LoRA from these images", "fine-tune on our look", "a custom model that draws in our style", or "consistent illustrations at scale". An async training job, not one-shot generation. To upload a model you already trained elsewhere, use bring-your-own-model. For same-identity output without training, use character-consistency.