Seedream 5.5 is live on Atlas Cloud — native transparent PNG & 80+ round editing
Home
Explore
Kwaivgi
Kling 4.0
kwaivgi/kling-v4.0/reference-to-video
Atlas Cloud GeneratorUnlock your potential as a director.Go Create
Kling Video 4.0 Reference-to-Video
image-to-video

Kling Video 4.0 Reference-to-Video API by Kuaishou

kwaivgi/kling-v4.0/reference-to-video
Reference-to-video

Kling 4.0 Omni Reference combines up to 15 images, videos, subjects and voices to generate a consistent 3-30 second video.

Kling Video 4.0 Reference-to-Video is developed by Kuaishou. Atlas Cloud (operated by Atlas Cloud AI LLC) provides access to it and does not own it. All trademarks belong to their respective owners.

Kling Video 4.0 Reference-to-Video

Kling Video 4.0 Reference-to-Video (Omni Reference) generates a 3–30 second video that stays consistent with everything you give it: reference images, reference videos, Kling subjects and voices — up to 15 references in one request.

Why Choose This?

  • Omni reference. Mix up to 10 images, 5 videos, 7 subjects and 3 voices (15 items in total).
  • Motion and style transfer. Reference videos carry motion rhythm, camera work or style into the new clip.
  • Consistent characters. Define subjects (elements) from images or a short video clip in the request, and they stay consistent throughout the clip.
  • Keyframes too. Optionally pin a first, middle or last frame.

Parameters

ParameterRequiredDescription
modelYeskwaivgi/kling-v4.0/reference-to-video
promptYesScene description. Refer to inputs with @image_N, @video_N, @element_N, @voice_N.
reference_imagesNoReference images (URLs or Base64).
reference_videosNoFeature reference videos. MP4 / MOV, 3–30s in total.
elementsNoSubjects created for this request from images or a video clip (see Notes).
voice_idsNoKling voice IDs (custom or preset), up to 3.
image / middle_images / last_imageNoOptional keyframes.
durationNoVideo length in seconds, integer 3–30. Default 5.
aspect_ratioNoauto (default, adapts to the references), 16:9, 9:16, 1:1, 21:9.
resolutionNoNative 720p or 1080p (default); Tencent ESR 1080p-esr, 2k-esr, or 4k-esr.

Reference numbering: images are numbered keyframes first (first → middle → last), then reference_images; videos, subjects and voices are numbered in array order. If the prompt mentions none of the reference images, videos, subjects or voices, all of them are referenced automatically.

How to Use

curl -X POST "https://api.atlascloud.ai/api/v1/model/generateVideo" \ -H "Authorization: Bearer $AIP_API_KEY" \ -H "Content-Type: application/json" \ --data-raw '{ "model": "kwaivgi/kling-v4.0/reference-to-video", "prompt": "The man in @image_1 walks through a park at golden hour, following the motion rhythm of @video_1. Photorealistic style.", "reference_images": ["https://p2-kling.klingai.com/kcdn/cdn-kcdn112452/kling-qa-test/man.jpeg"], "reference_videos": ["https://p2-kling.klingai.com/kcdn/cdn-kcdn112452/kling-qa-test/animals-video-5s.mp4"], "duration": 5, "aspect_ratio": "auto", "resolution": "1080p" }'

Generation is asynchronous. The response contains a request id; poll GET https://api.atlascloud.ai/api/v1/model/prediction/{id} until status is completed, then read the video URL from outputs.

Notes

  • Preview. Kling 4.0 is in early access upstream; pricing and limits follow Kling's preview terms and may change.
  • The Kling 4.0 API has no audio on/off or multi_shot parameter; describe sound and shot structure in the prompt.
  • duration must be an integer from 3 to 30. Supported resolutions are 720p, 1080p, 1080p-esr, 2k-esr, and 4k-esr.
  • ESR choices generate a Kling source video, then enhance it with Tencent ESR: 1080p-esr uses a native 720p source; 2k-esr and 4k-esr use a native 1080p source. These are enhanced outputs.
  • 2k-esr targets 1440p (2560×1440 at 16:9); 4k-esr targets 2160p (3840×2160 at 16:9). The source aspect ratio and frame rate are preserved; portrait outputs use the corresponding short-edge target.
  • ESR pricing adds an enhancement charge for output seconds to the source-generation price. Video-input billing still applies to source generation; the enhancement charge is not multiplied by input-video duration. ESR requires an additional processing stage, so completion can take longer than native generation.
  • The output video is transferred to AtlasCloud storage before it is returned.
  • Subjects (elements): describe each subject in the request with element_name (and an optional element_description) plus reference_type — image_refer: frontal_image + 1–3 refer_images; video_refer: one 3–8s refer_videos clip of a real person. The subjects are created first and the video is generated right after, in the same request; this adds a short wait before generation starts.
  • Subjects are created anew for every request and are not saved: no subject ID is returned, and there is no element_id to reuse. To keep a character consistent across generations, send the same subject images or clip again.
  • Limits per request: up to 10 images (keyframes + reference images), 5 videos (3–30s in total), 7 subjects (at most 3 video character subjects), 3 voices, and 15 items in total.
  • The refer_videos clips of video subjects count toward the billed input video duration.

Explore Similar Models

One API for All Media AI.

Explore all models