GET

/v1/schemas/fal/video/kling/v4/reference-to-video

Accept:

kind inputactivity videohash 410048df…extracted Oct 27, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `7f4ea986cf60e4ce108048c3bf02f463748620a9361e2fbf222a88b953d6d38c` { "fetchedAt": 1793077201, "extractorVersion": "1", "verifiedAt": null }

Request body

12 properties · 0 required · 2 $defs

property	type	description	constraints
prompt	string	Text prompt. Reference inputs as @Image1, @Video1, @Element1, etc. Either prompt or multi_prompt must be provided.	length ≤ 26000 · nullable
duration	integer	Video duration in seconds (3-30).	3 ≤ n ≤ 30 · default: 5
end_image_url	string	Optional image to use as the last frame. Counts toward the image reference limit.	nullable
middle_image_urls	string[]	Optional ordered keyframes between the first and last frames (max 8). Count toward the image reference limit.	items ≤ 8 · nullable
resolution	enum	Output resolution.	720p \| 1080p · default: "1080p"
video_urls	string[]	Reference videos (3-30s each, 30s combined with element videos), referenced as @Video1, @Video2, ... (max 5).	items ≤ 5 · nullable
image_urls	string[]	Reference images, referenced as @Image1, @Image2, ... (max 10).	items ≤ 10 · nullable
aspect_ratio	enum	Aspect ratio of the generated video. 'auto' adapts it to the references.	auto \| 16:9 \| 9:16 \| 1:1 \| 21:9 · default: "16:9"
multi_prompt	KlingV4Shot[]	Per-shot prompts for multi-shot generation. The video duration is the sum of the shot durations.	items ≥ 1 · nullable
start_image_url	string	Optional image to use as the first frame. Counts toward the image reference limit.	nullable
voice_ids	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	items ≤ 3 · nullable
elements	KlingV4Element[]	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.	items ≤ 7 · nullable

Types

2 $defs

KlingV4Elementobject

frontal_image_url	string	The frontal image of the element (main view).	nullable
voice_id	string	Voice bound to this element. Create one with https://fal.ai/models/fal-ai/kling-video/create-voice	nullable
reference_image_urls	string[]	Additional views of the element from different angles (1-3).	items ≤ 3 · nullable
video_url	string	A video of the element, used instead of images (3-8s).	nullable

KlingV4Shotobject

duration	integer	Shot duration in seconds.	1 ≤ n ≤ 30 · default: 5
prompt*	string	The prompt for this shot.	length ≥ 1 · length ≤ 512

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"kling/v4/reference-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}