infery
← All models
Kling V3 Omni Video

Kling V3 Omni Video

kling-v3-omni-video

Video generationby Kwaivgi

Generate and edit cinematic video from text, images, and video references. Character consistency, multi-shot control, video editing, and native audio in one model.

Example

Details

Accepts
text + image + video

Pricing

Price
21 cr / second

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
modeenum: standard, pro, 4k'standard' generates 720p, 'pro' generates 1080p, '4k' generates 4K. 4K does not support reference_video.
promptrequiredstringText prompt for video generation. Supports <<<image_1>>>, <<<video_1>>> template references. Max 2500 characters.
durationintegerVideo duration in seconds (3-15). Ignored for video editing (base).
end_imagestringLast frame image. Requires start_image. Supports .jpg/.jpeg/.png, max 10MB, min 300px.
start_imagestringFirst frame image. Supports .jpg/.jpeg/.png, max 10MB, min 300px, aspect ratio 1:2.5 to 2.5:1.
aspect_ratioenum: 16:9, 9:16, 1:1Aspect ratio. Required when not using start frame or video editing.
multi_promptstringJSON array of shot definitions for multi-shot mode. Each shot: {"prompt": "...", "duration": N}. Max 6 shots, min duration 1s per shot, total must equal duration. Example: [{"prompt":"A cat jumps","duration":3},{"prompt":"It lands","duration":2}]
generate_audiobooleanGenerate native audio. Mutually exclusive with reference video.
reference_videostringReference video (.mp4/.mov). Duration 3-10s, resolution 720-2160px per side, max 200MB.
reference_imagesarrayReference images for elements, scenes, or styles. Supports .jpg/.jpeg/.png. Max 7 without video, 4 with video.
keep_original_soundbooleanKeep original sound from reference video.
video_reference_typeenum: feature, baseHow to use reference video: 'feature' for style/camera reference, 'base' for video editing.