ComfyUI Node
Kling O3 · Reference to Video
Kling’s unified model: create, animate, reference and edit up to 4K From 10.08 credits ($0.1008) per second. Model: kling/o3/reference-to-video Fields, prices and examples: https://popnow.ai/docs/models/kling-o3
Kling O3 · Reference to Video
- reference_image_urls
- reference_video_urls
- video
- task id
◄prompt►
◄elements►
◄aspect_ratio16:9►
◄resolution720p►
◄generate_audiofalse►
◄keep_original_audiotrue►
◄duration_seconds5►
◄shot_typesingle►
◄multi_prompt►
CategoryPopNow/Video/Kuaishou
Inputs (11)
| Name | Type | Default | Description |
|---|---|---|---|
| prompt | STRING | Say who and what each reference is (<<<image_1>>>, <<<image_2>>> and so on) and describe the shot they should produce. | |
| reference_image_urls | COMFY_AUTOGROW_V3 | Reference images for characters, objects, outfits or places, up to 7. Refer to them in the prompt as <<<image_1>>>, <<<image_2>>> and so on. | |
| elements | STRING | One named subject built from 2 to 4 images of the same character or object. Write @name in the prompt where it should appear. 4K only. JSON. A list of objects with "description", "end_ms"?, "image_urls", "name", "reference_audio_urls"?, "start_ms"?. | |
| aspect_ratio | COMBO | 16:9 | Output aspect ratio. |
| resolution | COMBO | 720p | Output resolution. Higher tiers cost more per second. |
| generate_audio | BOOLEAN | false | Generate a native soundtrack (voices, effects, ambience) with the picture. Audio costs more per second. Not available with a reference video. |
| keep_original_audio | BOOLEAN | true | Keep the reference video's own sound in the result. Only matters when a reference video is given. |
| duration_seconds | INT | 53–15 | Output length in whole seconds, from 3 to 15. Billed per second. |
| shot_type | COMBO | single | single keeps one continuous shot; multi lets the model cut the prompt into several shots on its own; customize follows the shot list you give in multi_prompt. |
| multi_prompt | STRING | Shot list for shot_type customize: one entry per shot, in order, each with its own prompt and length in seconds. The lengths must add up to duration_seconds. JSON. A list of objects with "duration_seconds", "prompt". | |
| reference_video_urlsopt | COMFY_AUTOGROW_V3 | Optional reference video (one clip) whose motion, camera or characters the new shot should draw on. Refer to it in the prompt as <<<video_1>>>. With a video, use up to 4 reference images. A run with a reference video is billed at a higher per-second rate. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| video | VIDEO | — |
| task id | STRING | The PopNow task id, for the API console logs or support. |