← All models
Wan 2.6 reference-to-video model.
Example
Details
- Accepts
- video
Pricing
- Price
- 12.5 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | — | Random seed for reproducibility. If None, a random seed is chosen. |
| promptrequired | string | Use @Video1, @Video2, @Video3 to reference subjects from your videos. Works for people, animals, or objects. For multi-shot prompts: '[0-3s] Shot 1. [3-6s] Shot 2.' Max 1500 characters. |
| duration | stringenum: 5, 10 | Duration of the generated video in seconds. R2V supports only 5 or 10 seconds (no 15s). |
| resolution | stringenum: 720p, 1080p | Video resolution tier. R2V only supports 720p and 1080p (no 480p). |
| video_urlsrequired | array | Reference videos for subject consistency (1-3 videos). Videos' FPS must be at least 16 FPS.Reference in prompt as @Video1, @Video2, @Video3. Works for people, animals, or objects. |
| multi_shots | boolean | When true (default), enables intelligent multi-shot segmentation for coherent narrative videos with multiple shots. When false, generates single continuous shot. Only active when enable_prompt_expansion is True. |
| aspect_ratio | stringenum: 16:9, 9:16, 1:1, 4:3, 3:4 | The aspect ratio of the generated video. |
| negative_prompt | — | Negative prompt to describe content to avoid. Max 500 characters. |
| enable_safety_checker | boolean | If set to true, the safety checker will be enabled. Disabling it requires account authorization; unauthorized requests are always checked. |
| enable_prompt_expansion | boolean | Whether to enable prompt rewriting using LLM. |
Output
| Field | Type | Description |
|---|---|---|
| seed | integer | The seed used for generation |
| video | — | The generated video file |
| actual_prompt | — | The actual prompt used if prompt rewriting was enabled |