ComfyUI Node
Kling O3 Image-to-Video
A ComfyUI node in ERPK/WaveSpeedAI with 13 inputs and 1 output.
Kling O3 Image-to-Video
- image
- end_image
- client
- video_url
◄modelKling O3►
◄prompt►
◄image_url►
◄duration5►
◄seed-1►
◄end_image_url►
◄soundfalse►
◄shot_typeintelligent►
◄multi_prompt►
◄element_list►
CategoryERPK/WaveSpeedAI
Inputs (13)
| Name | Type | Default | Description |
|---|---|---|---|
| model | COMBO | Kling O3 | Model variant: Kling O3 (standard) or Kling O3 Pro (adds element_list) |
| prompt | STRING | Text description of motion, camera movement, and action | |
| image_url | STRING | Starting image URL (use WaveSpeed Upload Image to produce one). Fallback when the IMAGE input is not connected. | |
| imageopt | IMAGE | Starting image as a ComfyUI IMAGE tensor. Preferred — takes precedence over `image_url` when connected. | |
| end_imageopt | IMAGE | Optional end-frame image as a ComfyUI IMAGE tensor for guided transitions. Preferred — takes precedence over `end_image_url` when connected. | |
| clientopt | WAVESPEED_AI_API_CLIENT | WaveSpeed API client (optional if API key is configured in Settings) | |
| durationopt | INT | 53–15 | Video duration in seconds. Std accepts 3-15; Pro accepts 5 or 10. |
| seedopt | INT | -1-1–2147483647 | Retained for workflow compatibility; the O3 API does not accept a seed parameter. |
| end_image_urlopt | STRING | End-frame image URL for guided transitions. Fallback when the end_image IMAGE input is not connected. | |
| soundopt | BOOLEAN | false | Enable synchronized audio generation (raises base cost) |
| shot_typeopt | COMBO | intelligent | Shot composition mode: 'intelligent' (auto) or 'customize' (manual) |
| multi_promptopt | STRING | JSON array of scene-segmented prompts guiding scene transitions | |
| element_listopt | STRING | Pro only: JSON array of Kling Elements IDs to lock for visual consistency |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| video_url | STRING | — |