ComfyUI Node
Kling 2.6 Image-to-Video
A ComfyUI node in ERPK/WaveSpeedAI with 12 inputs and 1 output.
Kling 2.6 Image-to-Video
- image
- end_image
- client
- video_url
◄modelKling 2.6►
◄prompt►
◄image_url►
◄negative_prompt►
◄duration5►
◄end_image_url►
◄cfg_scale0.50►
◄soundtrue►
◄seed-1►
CategoryERPK/WaveSpeedAI
Inputs (12)
| Name | Type | Default | Description |
|---|---|---|---|
| model | COMBO | Kling 2.6 | Model variant: Kling 2.6 (Std) or Kling 2.6 Pro (cfg_scale, end_image, sound) |
| prompt | STRING | Text description of scene motion, camera moves, and audio | |
| image_url | STRING | Starting image URL (JPG/JPEG/PNG, max 10MB, min 300px each side, aspect 1:2.5-2.5:1). 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 | Pro only: end-frame image as a ComfyUI IMAGE tensor. Preferred — takes precedence over `end_image_url` when connected. Cannot be combined with sound. | |
| clientopt | WAVESPEED_AI_API_CLIENT | WaveSpeed API client (optional if API key is configured in Settings) | |
| negative_promptopt | STRING | Elements to exclude from visuals and audio | |
| durationopt | COMBO | 5 | Video duration in seconds (5 or 10) |
| end_image_urlopt | STRING | Pro only: end-frame URL; cannot be combined with sound. Fallback when the end_image IMAGE input is not connected. | |
| cfg_scaleopt | FLOAT | 0.500.3–0.8 | Pro only: guidance strength (0.3-0.8); higher follows the prompt more closely |
| soundopt | BOOLEAN | true | Pro only: enable joint audio-video generation (doubles cost); cannot be combined with end_image |
| seedopt | INT | -1-1–2147483647 | Cache control: randomize re-runs generation each queue; a fixed value reuses the cached video. This endpoint has no seed parameter, so it is not sent to the API. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| video_url | STRING | — |