AI Studio: generate image/video (async)
studio_generateGenerate AI images or videos with a model from list_studio_models — or apply a preset from list_studio_presets (then model_key and params default to the preset's, and prompt describes the {subject}). Image-to-video and edits need start_upload_id (an image uploaded with POST /api/v1/uploads). Costs the model's price × count (check with estimate_credits, action=studio); failed generations are refunded. Returns generation ids immediately; poll get_generation until status is complete.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | Number of variations (image models only, 1–4). | |
| params | No | Model params by key (duration, resolution, aspect_ratio, audio, seed…), see list_studio_models. | |
| prompt | No | What to generate. With a preset: who/what the {subject} is (e.g. “a young singer in a red dress”). | |
| model_key | No | Model key from list_studio_models (optional with preset_id). | |
| preset_id | No | Preset id from list_studio_presets. | |
| end_upload_id | No | End frame upload id (models that support it). | |
| preset_values | No | Values for other template placeholders, e.g. {"outfit": "a gold suit"}. | |
| idempotency_key | No | Optional unique key (e.g. a uuid) — repeating the same call with the same key within 24 h returns the first result instead of charging again. | |
| negative_prompt | No | What to avoid (models that support it). | |
| start_upload_id | No | Start frame / source image upload id. | |
| reference_upload_ids | No | Reference image upload ids. |