Kling O3 4K Image to Video API

kwaivgi/kling-video-o3-4k/image-to-video

Generate 3–15-second videos with Kling O3 4K from a starting image and an optional ending frame. Outputs 4K video. Supports single-shot and multi-shot generation. Explicitly set sound; multi-shot requires audio.

Input

Prompt(Required)

Multi Shots

470/2,500

Image Urls[0]

Image Urls[1] (optional)

Upload

Duration

Sound

Output

Ready

Continue using

Kling O3 4K Text to Video Kling O3 Pro Image to Video Kling O3 Standard Image to Video Kling O3 Pro Text to Video

REST API Reference

Quick Start

Submit a task and query its status.

Step 1: Set up authentication

Create an API key in the dashboard and attach Authorization: Bearer <API_KEY> when submitting a task.

Submit Endpoint: POSThttps://api.vidgo.ai/api/generate/submit
Authorization Header: Authorization: Bearer VIDGO_API_KEY

Step 2: Submit a task

POST /api/generate/submit: kwaivgi/kling-video-o3-4k/image-to-video

Submit Request

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "kwaivgi/kling-video-o3-4k/image-to-video",
  "input": {
    "duration": 4,
    "sound": true,
    "multi_shots": false,
    "prompt": "Begin with the supplied botanical macro. The foreground Venus flytrap slowly closes its two lobes around their central hinge, ending with marginal cilia interlaced. Preserve its vein pattern, dew beads, surrounding leaves and blurred greenhouse glazing. Droplet highlights shift naturally. Fixed macro camera, realistic plant motion; no insect, animal features or new leaves. Audio: quiet greenhouse ambience and one distant drip; no music. No text, logos or watermarks.",
    "image_urls": [
      "https://cdn.vidgo.ai/apis/models/kwaivgi/kling-video-o3-4k/image-to-video/v1/01/input-start.png"
    ]
  }
}
JSON
)

RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data "$REQUEST_BODY")

CODE=$(printf '%s' "$RESPONSE" | jq -r '.code // empty')
if [ "$CODE" != "0" ] && [ "$CODE" != "200" ]; then
  printf 'API error: %s
' "$RESPONSE" >&2
  exit 1
fi
printf '%s
' "$RESPONSE"

Step 3: Poll for completion

Poll with task_id while status is not_started or running, and stop at finished or failed. On success, read data.files[].file_url; on failure, read data.error_message.

Status Endpoint

GET https://api.vidgo.ai/api/generate/status/{task_id}

Poll with task_id while status is not_started or running, and stop at finished or failed. On success, read data.files[].file_url; on failure, read data.error_message.

not_startedrunningfinishedfailed

Submit Response

{
  "code": 200,
  "data": {
    "task_id": "task-submitted-example",
    "status": "not_started",
    "created_time": "2026-09-22T00:00:00Z"
  }
}

Completed Response

{
  "code": 200,
  "data": {
    "task_id": "MQX9Q1HSIUMLPP44",
    "status": "finished",
    "files": [
      {
        "file_type": "video",
        "file_url": "https://cdn.vidgo.ai/apis/models/kwaivgi/kling-video-o3-4k/image-to-video/v1/01/output.mp4"
      }
    ],
    "created_time": "2026-09-22T18:50:38",
    "error_message": null,
    "progress": 100
  }
}

Complete executable script

Expand to review an end-to-end script with automatic polling, error handling, and timeout safeguards.

Complete executable script

set -euo pipefail
: "${VIDGO_API_KEY:?Set VIDGO_API_KEY in your environment}"

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "kwaivgi/kling-video-o3-4k/image-to-video",
  "input": {
    "duration": 4,
    "sound": true,
    "multi_shots": false,
    "prompt": "Begin with the supplied botanical macro. The foreground Venus flytrap slowly closes its two lobes around their central hinge, ending with marginal cilia interlaced. Preserve its vein pattern, dew beads, surrounding leaves and blurred greenhouse glazing. Droplet highlights shift naturally. Fixed macro camera, realistic plant motion; no insect, animal features or new leaves. Audio: quiet greenhouse ambience and one distant drip; no music. No text, logos or watermarks.",
    "image_urls": [
      "https://cdn.vidgo.ai/apis/models/kwaivgi/kling-video-o3-4k/image-to-video/v1/01/input-start.png"
    ]
  }
}
JSON
)

SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data "$REQUEST_BODY")

TASK_ID=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.data.task_id // .task_id // empty')
BUSINESS_CODE=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.code // empty')
if [ "$BUSINESS_CODE" != "0" ] && [ "$BUSINESS_CODE" != "200" ]; then
  printf 'Submit failed:
%s
' "$SUBMIT_RESPONSE" >&2
  exit 1
fi
if [ -z "$TASK_ID" ]; then
  printf 'Submit response did not include task_id:
%s
' "$SUBMIT_RESPONSE" >&2
  exit 1
fi

START_TIME=$(date +%s)
POLL_DELAY=2
while true; do
  if [ $(( $(date +%s) - START_TIME )) -ge 600 ]; then
    printf 'Timed out after 600 seconds
' >&2
    exit 1
  fi
  STATUS_RESPONSE=$(curl --silent --show-error --fail-with-body \
    --url "https://api.vidgo.ai/api/generate/status/$TASK_ID" \
    --header "Authorization: Bearer $VIDGO_API_KEY")
  STATUS=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.data.status // .status // empty')
  BUSINESS_CODE=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.code // empty')
  if [ "$BUSINESS_CODE" != "0" ] && [ "$BUSINESS_CODE" != "200" ]; then
    printf 'Status request failed:
%s
' "$STATUS_RESPONSE" >&2
    exit 1
  fi

  case "$STATUS" in
    finished)
      printf '%s' "$STATUS_RESPONSE" | jq -r '(.data.files // .files // [])[]?.file_url'
      break
      ;;
    failed)
      printf '%s' "$STATUS_RESPONSE" | jq -r '.data.error_message // .error_message // "Generation failed"' >&2
      exit 1
      ;;
    not_started|running)
      sleep "$POLL_DELAY"
      if [ "$POLL_DELAY" -lt 10 ]; then POLL_DELAY=$((POLL_DELAY + 1)); fi
      ;;
    *)
      printf 'Unexpected task status: %s
' "$STATUS" >&2
      exit 1
      ;;
  esac
done

Request Parameters (input object)

Put generation parameters inside input. Use standard JSON numbers and booleans. For compatibility, integer strings such as "5" are accepted. Boolean strings true/1/yes/y/on mean true; false/0/no/n/off mean false. These strings are case-insensitive and trimmed. Numeric 1 and 0 are also accepted for boolean fields. Numeric and boolean prompt values are converted to text; 0, false and null are treated as empty. Objects and arrays are not accepted as prompts. The API validates prompts up to 2,500 characters. Some multi-shot generation requests have failed when a shot prompt exceeded 512 characters. We recommend keeping each shot prompt within 512 characters; this recommendation does not change the API validation limit.

Field	Type	Required	Default	Description
prompt	string	Conditional	-	Required when multi_shots=false. Describe the scene, action and camera movement. Use nonblank text, up to 2,500 characters after trimming. Omit prompt when multi_shots=true.
multi_shots	boolean	Yes	-	Required: explicitly send false for a single shot or true for multiple shots. Single-shot mode requires prompt. Multi-shot mode requires multi_prompt and sound=true, with no nonblank top-level prompt. Omitting this field is an error.
multi_prompt	array	Conditional	-	Required when multi_shots=true; omit in single-shot mode. Supply at least one shot, each with a nonblank prompt of up to 2,500 characters and an integer duration of 1–12 seconds. Shot durations must sum to the top-level duration (3–15 seconds). Extra fields inside a shot are ignored.
duration	integer	Yes	-	Required integer from 3 to 15 seconds. In multi-shot mode, this must equal the sum of all shot durations. Credits are calculated using this value.
sound	boolean	Yes	-	Required: explicitly send true to generate audio or false for video without audio. Single-shot mode accepts either value; multi-shot mode requires true.
aspect_ratio	string	No	-	May be omitted. If provided, use 16:9, 9:16 or 1:1. Image-to-video ignores this value; framing is determined by the input image.
image_urls	array	Yes	-	Required: an array of 1–2 images. The first is the starting frame; the optional second is the ending frame. Accepts public HTTP(S) URLs, image Data URIs or raw Base64 image data.

Response Fields (Status Query)

Details returned by GET /api/generate/status/{task_id}:

Field	Type	Description
code	integer	HTTP/business response status code (200 indicates success).
data.task_id	string	Globally unique task identifier.
data.status	string	Task lifecycle state: not_started, running, finished, or failed.
data.files	array	Array of output assets containing file_url and file_type upon completion.
data.error_message	string \| null	Error diagnostic details if the task status is failed.

Task Lifecycle

Clients should poll status until reaching either the finished or failed terminal state:

not_started
Queued
running
Generating
finished
Ready
failed
Failed

Polling & Error Handling

Polling frequencyStart polling with a 2 to 3-second interval, gradually increasing to 5 seconds for extended takes.
Network resiliencyTransient 5xx responses or timeouts do not signify task failure; retry status requests after a short backoff.
Webhook callbacksProvide a top-level callback_url in your submission payload to receive completion notifications automatically.

Specifications

Specification	Value	Description
Model	kwaivgi/kling-video-o3-4k/image-to-video	Kuaishou Kling O3 flagship native 4K image-to-video tier supporting single-frame initiation and dual-keyframe physical motion interpolation with native multimodal audio.
Duration	3-15 s	Required integer, 3–15 seconds. In multi-shot mode it must equal the sum of shot durations. Billing uses this duration.

Kling O3 4K Image to Video API docs

Kling O3 4K Image to Video

Why Choose This Model

Native 4K Dual-Keyframe InterpolationAnchors starting and ending frame coordinates in 3840×2160 resolution, synthesizing realistic intermediate physical acceleration and light transport.
Micro-Texture & Ray-Tracing FidelityPreserves micro-pores, fine fabric weaves, subtle scratches on metal, and specular highlights without blurriness or compression noise.
Extreme Subject Asset AnchoringDeep feature tracking networks lock character facial geometry and industrial product specifications firmly in place without anatomical drift.
Native Panoramic Action AudioSynthesizes multi-channel ambient acoustics, physical Foley impacts, and lip-sync dialogue directly aligned with 4K motion trajectories.
Commercial Broadcast-Ready MastersDelivers clean, uncompressed-quality MP4 masters ready for theatrical exhibition, high-end color grading suites, and outdoor displays.

Parameters

Parameter	Requirement	Description
prompt	Conditional	Required when multi_shots=false. Describe the scene, action and camera movement. Use nonblank text, up to 2,500 characters after trimming. Omit prompt when multi_shots=true. Default`-`
multi_shots	Yes	Required: explicitly send false for a single shot or true for multiple shots. Single-shot mode requires prompt. Multi-shot mode requires multi_prompt and sound=true, with no nonblank top-level prompt. Omitting this field is an error. Default`-`
multi_prompt	Conditional	Required when multi_shots=true; omit in single-shot mode. Supply at least one shot, each with a nonblank prompt of up to 2,500 characters and an integer duration of 1–12 seconds. Shot durations must sum to the top-level duration (3–15 seconds). Extra fields inside a shot are ignored. Default`-`
duration	Yes	Required integer from 3 to 15 seconds. In multi-shot mode, this must equal the sum of all shot durations. Credits are calculated using this value. Default`-`
sound	Yes	Required: explicitly send true to generate audio or false for video without audio. Single-shot mode accepts either value; multi-shot mode requires true. Default`-`
aspect_ratio	No	May be omitted. If provided, use 16:9, 9:16 or 1:1. Image-to-video ignores this value; framing is determined by the input image. Default`-`
image_urls	Yes	Required: an array of 1–2 images. The first is the starting frame; the optional second is the ending frame. Accepts public HTTP(S) URLs, image Data URIs or raw Base64 image data. Default`-`

How to Use

Prepare 4K source stillsUpload 1 initial reference still (required), and optionally upload 1 ending still to anchor the terminal state and camera framing.
Direct motion and camera pathsDescribe transitional physical motion, camera velocity, and lighting evolutions connecting the keyframes.
Set runtime and audio channelChoose an integer duration from 3 to 15 seconds, and activate sound=true to synthesize synchronized spatial audio.
Initiate 4K diffusion renderingSubmit via API or playground; the engine executes spatio-temporal physical trajectory calculations directly in 4K resolution.
Inspect micro-textures and exportReview the rendered take for anatomical stability and micro-texture fidelity, then download your 4K MP4 master.

Pricing

Credits = top-level duration × per-second rate. 1 credit = $0.005. If generation fails, consumed credits are automatically and fully refunded.

Usage	Rate	Details
Without sound	50 credits/s ($0.250/s)	Native 4K keyframe physical motion interpolation without audio.
With sound	50 credits/s ($0.250/s)	Native 4K video integrated with high-fidelity action Foley and spatial sound.

Best Use Cases

Luxury & High-End Industrial CommercialsConvert ultra-resolution jewelry, horology, and automotive renders into broadcast-ready 4K cinematic sequences.
VFX Keyframe Complex TransitionsInterpolate complex, physically plausible visual effects between detailed opening and closing concept artwork.
Giant-Screen Installations & Digital ArtAnimate digital paintings and historical artworks at true 4K resolution for museum displays and immersive spaces.
Photorealistic Virtual Human CampaignsMaintain virtual persona micro-facial geometry, hair fidelity, and skin tone while introducing expressive movement.

Pro Tips

Upload source images with native 2K or 4K resolution; rich initial texture priors enable the diffusion model to produce stunningly lifelike results.
When using dual keyframes, ensure camera angle shifts between images stay within 90 degrees to maintain structural fidelity.
Focus your prompt on the mechanics of physical transition (e.g., "gentle breeze rustling hair, eyes turning warmly toward the lens").
For character dialogue, enclose spoken lines in quotation marks; the 4K lip-sync engine computes subtle articulatory facial movements.
Select at least 5 seconds of duration for intricate 4K dynamics, allowing acceleration curves and physical momentum to resolve naturally.

Notes

image_urls supports 1 to 2 images. The output aspect ratio naturally reflects source image dimensions.
Multi-shot mode requires sound=true and mandates that individual shot durations sum exactly to the overall duration.
Native 4K generation is computationally intensive; maintain appropriate client polling timeout windows.

Kling O3 4K Image to Video API FAQ

What does this endpoint generate?

How do I use starting and ending frames?

Required: an array of 1–2 images. The first is the starting frame; the optional second is the ending frame. Accepts public HTTP(S) URLs, image Data URIs or raw Base64 image data.

How is the video aspect ratio determined?

May be omitted. If provided, use 16:9, 9:16 or 1:1. Image-to-video ignores this value; framing is determined by the input image.

How do I set up multiple shots?

Required: explicitly send false for a single shot or true for multiple shots. Single-shot mode requires prompt. Multi-shot mode requires multi_prompt and sound=true, with no nonblank top-level prompt. Omitting this field is an error. Required when multi_shots=true; omit in single-shot mode. Supply at least one shot, each with a nonblank prompt of up to 2,500 characters and an integer duration of 1–12 seconds. Shot durations must sum to the top-level duration (3–15 seconds). Extra fields inside a shot are ignored.

How do I control audio and prompt length?

Required: explicitly send true to generate audio or false for video without audio. Single-shot mode accepts either value; multi-shot mode requires true. The API validates prompts up to 2,500 characters. Some multi-shot generation requests have failed when a shot prompt exceeded 512 characters. We recommend keeping each shot prompt within 512 characters; this recommendation does not change the API validation limit.

How are duration and credits calculated?

Duration is 3–15 seconds. Video without audio costs 50 credits/s; video with audio costs 50 credits/s. Credits equal the top-level duration multiplied by the applicable rate.

What happens if generation fails or my request times out?

Invalid parameters are rejected before a generation task is created or credits are deducted. If an accepted generation task later reaches failed, its deducted credits are refunded. A client timeout alone does not mean the task failed; query its task_id before submitting again.