ComfyUI Node
Superside Kling 4 Reference-to-Video
Kling 4 Reference-to-Video on fal. Returns a native VIDEO plus the URL, so SaveVideo or PreviewVideo connects straight in. Endpoint: default - kling/v4/reference-to-video fal price (2026-10-30): Video costs $0.157 per second at 720p and $0.235 per second at 1080p. With video references or video elements, it costs $0.094 per second at 720p and $0.141 per second at 1080p, billed on the input plus output length (minimum 2x the output).
Superside Kling 4 Reference-to-Video
- image_1
- image_2
- image_3
- image_4
- end_image_url
- video_1
- video_2
- video_3
- video_4
- middle_image_1
- middle_image_2
- middle_image_3
- middle_image_4
- start_image_url
- video
- video_url
◄api_key►
◄prompt►
◄multi_prompt►
◄voice_ids►
◄duration5►
◄resolution1080p►
◄aspect_ratio16:9►
◄elements►
CategorySuperside
Inputs (22)
| Name | Type | Default | Description |
|---|---|---|---|
| api_key | STRING | — | |
| promptopt | STRING | Text prompt. Reference inputs as @Image1, @Video1, @Element1, etc. Either prompt or multi_prompt must be provided. | |
| image_1opt | IMAGE | Reference images, referenced as @Image1, @Image2, ... (max 10). | |
| image_2opt | IMAGE | Reference images, referenced as @Image1, @Image2, ... (max 10). | |
| image_3opt | IMAGE | Reference images, referenced as @Image1, @Image2, ... (max 10). | |
| image_4opt | IMAGE | Reference images, referenced as @Image1, @Image2, ... (max 10). | |
| end_image_urlopt | IMAGE | Optional image to use as the last frame. Counts toward the image reference limit. | |
| video_1opt | VIDEO | Reference videos (3-30s each, 30s combined with element videos), referenced as @Video1, @Video2, ... (max 5). | |
| video_2opt | VIDEO | Reference videos (3-30s each, 30s combined with element videos), referenced as @Video1, @Video2, ... (max 5). | |
| video_3opt | VIDEO | Reference videos (3-30s each, 30s combined with element videos), referenced as @Video1, @Video2, ... (max 5). | |
| video_4opt | VIDEO | Reference videos (3-30s each, 30s combined with element videos), referenced as @Video1, @Video2, ... (max 5). | |
| multi_promptopt | STRING | Per-shot prompts for multi-shot generation. The video duration is the sum of the shot durations. JSON, as fal documents this field. | |
| voice_idsopt | STRING | Voices referenced in the prompt as @Voice1, @Voice2, ... (max 3, including voices bound to elements). Create one with https://fal.ai/models/fal-ai/kling-video/create-voice Comma-separated. | |
| durationopt | INT | 53–30 | Video duration in seconds (3-30). |
| middle_image_1opt | IMAGE | Optional ordered keyframes between the first and last frames (max 8). Count toward the image reference limit. | |
| middle_image_2opt | IMAGE | Optional ordered keyframes between the first and last frames (max 8). Count toward the image reference limit. | |
| middle_image_3opt | IMAGE | Optional ordered keyframes between the first and last frames (max 8). Count toward the image reference limit. | |
| middle_image_4opt | IMAGE | Optional ordered keyframes between the first and last frames (max 8). Count toward the image reference limit. | |
| resolutionopt | COMBO | 1080p | Output resolution. |
| start_image_urlopt | IMAGE | Optional image to use as the first frame. Counts toward the image reference limit. | |
| aspect_ratioopt | COMBO | 16:9 | Aspect ratio of the generated video. 'auto' adapts it to the references. |
| elementsopt | STRING | Characters/objects, referenced as @Element1, @Element2, ... (max 7). Up to 3 elements may carry a voice_id and up to 3 may be video elements. JSON, as fal documents this field. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| video | VIDEO | — |
| video_url | STRING | — |