VidgoAI

Kling 4.0 Reference to Video API

kwaivgi/kling-v4.0/reference-to-video
720p / 1080p · 3–30 sec

Kling 4.0 Reference to Video turns reference images, videos and reusable elements into a 3–30 second 720p or 1080p video with stereo audio, cited as @Image1, @Video1 or @Element1. It keeps characters, products and settings consistent with your references inside the new scene you describe.

Input
503/26000

Drag and drop files, paste from clipboard, or provide a URL. Optional start frame: 1 JPEG, PNG or WebP image.

Drag and drop files, paste from clipboard, or provide a URL. Up to 10 images, cited in the prompt as @Image1, @Image2…

2/10 files added

Drag and drop files, paste from clipboard, or provide a URL. Up to 5 videos, 3–30 s each and 30 s combined, cited as @Video1… Billed as input video.

Switch to JSON to add kling_elements or multi-shot prompts with multi_prompt.

OutputExample
8 sec × $0.1425/sec = $1.140

With reference videos or video elements, the price uses the input-video rate: output seconds plus the longer of output seconds or total input video length. The final amount is set when the server measures the videos.

Continue with
Kling 4.0 Text to VideoKling 4.0 Image to VideoKling 4.0 Video EditKling 3.0 Turbo Pro Text to Video

Kling 4.0 Reference to Video

Kling 4.0, released by Kuaishou's Kling AI in October 2026, includes Omni Reference: up to 15 assets guide a single generation. Combine up to 10 images (including an optional start frame), 5 reference videos and 7 elements, where an element is one subject shown in 2–4 images or one video. Reference videos can carry motion and camera rhythm, and clips run up to 30 seconds with a stereo track.

Why choose the Kling 4.0 Reference to Video API?

  • Up to 15 references in one requestMix images, videos and elements to define who appears, where, and how they move.

  • Reusable subjects with elementsDescribe one character or product with 2–4 images and cite it as @Element1 across scenes.

  • Motion from reference videoPoint to a clip as @Video1 to borrow its movement or camera rhythm.

  • Clear, two-tier pricingImage-only references bill like text prompts; reference videos switch to the lower input-video rate on a published formula.

Parameters

ParameterRequirementDescription
promptRequired unless multi_prompt is sent

One prompt for the whole clip, 1–26,000 characters after trimming. Describe action, camera, and any dialogue, effects or ambience. Send either prompt or multi_prompt.

Default—
multi_promptRequired unless prompt is sent

A list of shots, each {prompt (1–512 characters), duration (1–30 s, default 5)}. Shot durations must total 3–30 seconds and set the clip length.

Default—
reference_image_urlsAt least one of the three reference fields

Up to 10 reference image URLs, cited in the prompt as @Image1, @Image2 and so on. Together with the optional start frame, at most 10 images.

Default—
reference_video_urlsAt least one of the three reference fields

Up to 5 reference video URLs, each 3–30 seconds, cited as @Video1 and so on. All input videos together run at most 30 seconds and are billed as input video.

Default—
kling_elementsAt least one of the three reference fields

Up to 7 reusable subjects, cited as @Element1 and so on. Each element has either element_input_urls (2–4 images of the same subject) or element_input_video_urls (exactly 1 video). Up to 3 elements can be video-based; those are billed as input video.

Default—
image_urlsOptional

Optional start frame: at most 1 image URL that opens the clip.

Default—
durationOptional

Output length in seconds, 3–30. With multi_prompt it defaults to the shot total.

Default5
resolutionOptional

720p or 1080p. The resolution sets the per-second rate.

Default720p
aspect_ratioOptional

auto, 16:9, 9:16, 1:1 or 21:9.

Defaultauto

How to Use

  1. Gather referencesChoose clear images of the subject and setting, short reference clips (3–30 s each), or build elements from 2–4 images of one subject.

  2. Cite each reference in the promptRefer to inputs by position, such as @Image1 for the face, @Image2 for the room and @Video1 for the dance.

  3. Set length, resolution and framePick 3–30 seconds, 720p or 1080p and an aspect ratio; add a start frame in image_urls if the clip should open on it.

  4. Submit and collect the videoSend the request, then poll with the task_id or wait for callback_url.

Usage and billing

With image references only, Kling 4.0 Reference to Video is billed per output second. Once any reference video or video element is included, the lower input-video rate applies to billed seconds: output seconds plus the longer of output seconds or the total input video length, rounded up. Example: 5 s of output with a 12 s reference video at 1080p bills 17 seconds, 433.5 credits ($2.1675).

UsageRateDetails
720p, image references only28.5 credits / second$0.1425 / output second. 5 seconds = 142.5 credits ($0.7125); 30 seconds = 855 credits ($4.275).
1080p, image references only42.5 credits / second$0.2125 / output second. 10 seconds = 425 credits ($2.125); 30 seconds = 1,275 credits ($6.375).
720p with input video17 credits / billed second$0.085 / billed second. Billed seconds = output seconds + the longer of output seconds or input video length (rounded up).
1080p with input video25.5 credits / billed second$0.1275 / billed second, same billed-seconds rule as 720p.

Best Use Cases

  • Character-consistent seriesReuse the same element across episodes, ads or social posts.

  • Product placement in new scenesKeep packaging and shape from product images while changing location and action.

  • Motion transferApply the movement in a reference video to a new character.

  • Scene assemblyCombine a character image, a location image and a prop image into one shot.

Pro Tips

  • Give each reference one job in the prompt, such as identity, setting or movement.
  • For an element, use 2–4 images of the same subject from different angles.
  • Keep reference videos short when only the motion matters; total input length affects the price.
  • Use image_urls for the start frame only when the clip must open on that exact image.

Notes

  • Send at least one of reference_image_urls, reference_video_urls or kling_elements, and exactly one of prompt or multi_prompt.
  • Limits: images including the start frame ≤10, reference videos ≤5, elements ≤7 (≤3 video-based), 15 assets in total.
  • Each input video runs 3–30 seconds, all input videos together at most 30 seconds, up to 100 MB each; the server measures their length.
  • Credits are reserved at submission using the measured video lengths.

Related Models

PixVerse V6 Max Text to Video previewPixVerse V6 Max Text to VideoPixVerse V6 Max Text to Video turns a prompt into 1–15 second videos at 360p to 1080p, with eight aspect ratios and an optional native audio track for dialogue, effects and music. Describe subjects, actions and sound in one prompt, then pick the length and format for each placement.
PixVerse V6 Max Image to Video previewPixVerse V6 Max Image to VideoPixVerse V6 Max Image to Video animates one JPEG, PNG or WebP image into a 1–15 second video at 360p to 1080p, with an optional native audio track. The image sets the subject and framing, and a prompt of up to 2,048 characters directs motion, camera and sound.
OmniHuman 2.0 Audio to Video previewOmniHuman 2.0 Audio to VideoOmniHuman 2.0 Audio to Video turns one character image and 4–300 seconds of speech or music into a 720p video, with lips, expression and gestures following the audio. The image keeps the character's look and framing, while an optional prompt adds camera moves and actions.
FLUX 3 Max Text to Video previewFLUX 3 Max Text to VideoFLUX 3 Max Text to Video turns a written shot into a 5–20 second 720p or 1080p video with native audio and eight aspect ratios. It follows the camera moves, lighting and sound cues you describe, so one prompt returns picture and audio together.
FLUX 3 Max Image to Video previewFLUX 3 Max Image to VideoFLUX 3 Max Image to Video animates a start image into a 5–20 second 720p or 1080p clip with native audio, optionally landing on an end frame you supply. It keeps the composition, subject and palette of your images while adding the motion and sound in the prompt.
FLUX 3 Max Keyframes to Video previewFLUX 3 Max Keyframes to VideoFLUX 3 Max Keyframes to Video turns 1–10 images pinned to exact frames into a single 5–20 second 720p or 1080p clip with native audio. Each image appears at the frame_index you set on a 24 fps timeline, so the story beats land where you planned them.
Kling 4.0 Text to Video previewKling 4.0 Text to VideoKling 4.0 Text to Video turns a prompt or multi-shot script into one 3–30 second 720p or 1080p video with stereo audio and five aspect ratios. It keeps scenes coherent across long takes and shot changes while following your camera, dialogue and sound directions.
Kling 4.0 Image to Video previewKling 4.0 Image to VideoKling 4.0 Image to Video animates a start image into a 3–30 second 720p or 1080p video with stereo audio, optionally finishing on an end frame you choose. It keeps the subject, framing and look of your image while adding the motion, camera work and sound in your prompt.
Kling 4.0 Video Edit previewKling 4.0 Video EditKling 4.0 Video Edit transforms an existing 3–30 second video from a written instruction, restyling scenes, swapping objects or adding elements at 720p or 1080p. It keeps the original timing, people and camera path that you ask to preserve while applying the change across every frame.
Vidu Q4 Image to Video previewVidu Q4 Image to VideoVidu Q4 Image to Video turns one start image and an optional motion prompt into a 3–16 second clip at 540p up to 4K. Your image sets the opening frame, so subject, setting and aspect ratio carry through while the prompt directs movement and camera.
Vidu Q4 Reference to Video previewVidu Q4 Reference to VideoVidu Q4 Reference to Video combines a prompt with up to 12 reference images and 3 voice clips into 3–16 second videos at up to 4K. Tag each reference in the prompt to keep characters, products and places recognisable, with optional generated audio at no extra cost.
Gemini Omni 1.1 Flash Text-to-Video previewGemini Omni 1.1 Flash Text-to-VideoGemini Omni 1.1 Flash Text-to-Video. Create 4–10 second videos with native audio from text, directing camera, lighting, and sound.
Gemini Omni 1.1 Flash Image-to-Video previewGemini Omni 1.1 Flash Image-to-VideoGemini Omni 1.1 Flash Image-to-Video. Animate a start image with native audio and add an optional end frame to guide the closing shot.
Gemini Omni 1.1 Flash Reference-to-Video previewGemini Omni 1.1 Flash Reference-to-VideoGemini Omni 1.1 Flash Reference-to-Video. Use 1–7 images to guide characters, products, and style in new video scenes with sound.
Gemini Omni 1.1 Flash Video Edit previewGemini Omni 1.1 Flash Video EditGemini Omni 1.1 Flash Video Edit. Edit 3–10 second videos through natural language with up to 5 reference images for visual guidance.
MiniMax H3 Max Turbo Text to Video previewMiniMax H3 Max Turbo Text to VideoMiniMax H3 Max Turbo Text to Video turns text into coherent 5–15 second videos with synchronized native stereo audio and fast generation. It follows physical motion while rendering subtle changes in light and shadow.

Kling 4.0 Reference to Video API FAQ

What is the Kling 4.0 Reference to Video API?

Kling 4.0 Reference to Video is a Kuaishou model for generating video guided by reference media, released by Kling AI in October 2026. It turns up to 10 images, 5 reference videos and 7 elements into a 3–30 second 720p or 1080p clip with a stereo audio track. Its Omni Reference input lets the prompt cite each asset as @Image1, @Video1 or @Element1, so identity, setting and motion come from the references you choose. You can call it programmatically or try it from the playground above.

How do I cite references in a Kling 4.0 Reference to Video prompt?

Refer to each input by its position in its list: @Image1 for the first reference image, @Video2 for the second reference video, @Element1 for the first element. Say what each one contributes, for example "@Image1 is the character, @Video1 is the dance".

How are reference videos billed in Kling 4.0 Reference to Video?

When a reference video or video element is present, you pay a lower rate (17 credits/s at 720p, 25.5 at 1080p) on billed seconds: output seconds plus the longer of output seconds or total input video length, rounded up. A 10-second 720p clip with a 3-second reference video bills 20 seconds, 340 credits ($1.70).

What are elements in Kling 4.0 Reference to Video?

An element is a reusable subject defined by element_input_urls with 2–4 images of the same character or object, or by element_input_video_urls with exactly one video. A request can hold up to 7 elements, at most 3 of them video-based.

How many references can Kling 4.0 Reference to Video use?

Up to 15 assets in total: at most 10 images including the optional start frame, 5 reference videos and 7 elements. Input videos each run 3–30 seconds and together at most 30 seconds.

How much does Kling 4.0 Reference to Video cost with image references only?

With images and image elements only, it bills like text-to-video: 28.5 credits per output second at 720p and 42.5 at 1080p. An 8-second 720p clip is 228 credits ($1.14).

Can Kling 4.0 Reference to Video start on a specific frame?

Yes. Put one image in image_urls to open the clip on it, alongside your references. It counts toward the 10-image limit.