Sign in
Training

Start a training run

Start training a custom style/LoRA from a reference set. Returns immediately with a run ID. Poll GET /workspaces/{workspace_id}/training-runs/{training_run_id} for progress. Creative Units are reserved at submission; call the estimate endpoint first to check cost.

post/v2/workspaces/{workspace_id}/training-runs

Path parameters

workspace_idstring uuid required

Id of the workspace that owns the resource.

Id of the workspace that owns the resource.

Headers

Idempotency-Keystring

Opaque key making this request safe to retry. The first request with a given key executes; a later request with the same key returns that first response with Idempotent-Replayed: true instead of executing again. The key covers the method, path, query, and body it was first used with; reusing it for a different request is rejected with 422. Replayable for 24 hours.

Request body

reference_set_idstring uuid required

The reference set (Style) to train a LoRA for.

base_model_idstring nullable

Base model to train. Omit to use the reference set's configured or workspace default model.

training_framework'fal' | 'ai-toolkit' nullable

Training framework override. Omit for the server default.

Response

Successful Response

training_run_idstring uuid required

Unique identifier for this training run.

state'in_progress' | 'terminal_success' | 'terminal_failure' required

Coarse state; in_progress right after submission.

raw_statusstring required

Fine-grained run status (e.g. initializing).

base_model_idstring nullable

Base model the run trains with.

created_atstring date-time required

Timestamp the run was created.

poll_interval_secondsinteger required

Suggested polling interval in seconds.

Changes