← All models
Generate high-quality video from a text prompt with Bernini-R, ByteDance's unified video generation and editing model.
Example
Details
- Accepts
- text
Pricing
- Price
- 10 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | — | Seed for reproducibility. Random when omitted. |
| promptrequired | string | Text prompt or editing instruction. |
| num_frames | integer | Number of frames. Snapped internally to 4k+1. |
| acceleration | stringenum: none, regular | Acceleration level. 'regular' enables MagCache step-skipping for faster generation at a small quality cost; 'none' (default) runs the full denoising schedule. |
| aspect_ratio | stringenum: 16:9, 9:16, 1:1 | Output aspect ratio. |
| max_image_size | integer | Long-edge size (px). Sets the output size for generation tasks and caps source/reference media for editing tasks. |
| negative_prompt | — | Negative prompt. Defaults to the standard Wan2.2 negative prompt. |
| frames_per_second | integer | Output frames per second. |
| num_inference_steps | integer | Number of denoising steps. |
| enable_prompt_expansion | boolean | Rewrite the prompt with an LLM before generation. The model is tuned on enhanced prompts; off by default. |
Output
| Field | Type | Description |
|---|---|---|
| seed | integer | Seed used for generation. |
| video | — | Generated / edited video. |
| actual_prompt | — | The final prompt after expansion (set only when prompt expansion ran). |