Train a custom style (LoRA) with simplified parameters. Uses intelligent defaults based on the training type (Default/Style/Object/Character).
| Model | Compute Units/Step |
|---|---|
| qwen | ~8.3 |
| wan22 | ~5.3 |
| k1 | ~3.4 |
| flux_schnell | ~3.4 |
| wan | ~3.4 |
| flux_dev | ~3.0 |
| z-image | ~2.4 |
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
URL to receive a POST request when the job completes. The webhook will receive the job data including results.
flux_dev, flux_schnell, wan, wan22 Style, Object, Character, Default 1 <= x <= 2000x >= 1Training job created successfully. The job will be in a pending state until completed. Use /jobs/{id} to check progress.