Start building

Kling 3.0 Omni Pro Image to Video

kwaivgi/kling-video/3.0/omni/pro/image-to-video

Kling Video Omni Pro is KwaiVGI's image-to-video AI model. Bring static images to life with fluid animation, consistent character motion, and professional-grade video output.

Use in agentGet API key
Base price
$0.56USD / run
Execution
async
Model type
video
Input fields
4

Try the model

Playground

Open playground
Input
Use @Image1 to reference the start frame, @Image2 to reference the end frame.

PNG, JPEG, WebP, or GIF · 20 MiB maximum

Image to use as the first frame of the video. Max file size: 10.0MB, Min width: 300px, Min height: 300px, Min aspect ratio: 0.40, Max aspect ratio: 2.50, Timeout: 20.0s

PNG, JPEG, WebP, or GIF · 20 MiB maximum

Image to use as the last frame of the video.
Video duration in seconds. Allowed values: 3, 4, 5, 6, 7, 8, 9, 10.
OutputReady

Your output will appear here

Complete the inputs, then click Run.

Specifications

Pricing

Base price
$0.56 / run
Billing formula
params.duration * 0.112

Context & modalities

Input
Schema-defined
Output
video

Capabilities

Chat
Not supported
Vision
Not supported
Reasoning
Not supported
Structured output
Not supported
Function calling
Not supported
Audio input
Not supported

Access

Provider
KwaiVGI
Model ID
kwaivgi/kling-video/3.0/omni/pro/image-to-video
Execution
async
API
Unified Run API
Endpoint
/v1/run

API README

Kling 3.0 Omni Pro Image to Video

Kling 3.0 Omni Pro Image to Video animates a required starting image into a directed video while preserving the visual identity, composition, and key details established by that frame. Add an optional ending image when the shot must arrive at a specific final composition, then use the prompt to describe the action, transformation, camera movement, lighting progression, and narrative connection between the two frames.

Built on Kling VIDEO 3.0 Omni's unified multimodal foundation, the model is designed for stronger semantic response, narrative control, and visual consistency across changing scenes. This route focuses that capability into a streamlined first-frame or first-and-last-frame workflow, making it practical for cinematic transitions, character and product animation, environmental transformations, and shots whose opening and ending beats must be planned in advance.

Highlights

  • Directed start-to-end transitions. Anchor the opening with image and optionally define the destination with end_image, giving the model clear visual boundaries for the shot.
  • Stronger subject consistency. Preserves recognizable character, object, and scene features as movement and camera perspective evolve across the generated sequence.
  • Narrative and semantic control. Responds to detailed instructions for staged action, scene progression, camera behavior, atmosphere, and visual transformation rather than applying generic motion.
  • Omni audiovisual foundation. Kling VIDEO 3.0 Omni is built for native audio-visual creation and coherent multi-shot storytelling; this API route packages its Pro image-to-video workflow around a prompt and frame controls.

Pricing

Billing is $0.112 per selected output second. The available durations and resulting request prices are listed below.

DurationPrice per request
3 seconds$0.336
4 seconds$0.448
5 seconds$0.560
6 seconds$0.672
7 seconds$0.784
8 seconds$0.896
9 seconds$1.008
10 seconds$1.120

When to Use

Use caseWhy this model fits
Character or product animationTurn a designed still into controlled motion while keeping its defining visual features recognizable.
First-to-last-frame transitionsSupply both endpoints for a transformation, reveal, pose change, or planned change in composition.
Seasonal and environmental changesDirect weather, time-of-day, material, or landscape progression from one visual state to another.
Cinematic camera movesDescribe pushes, pulls, orbits, tracking moves, reframing, and lighting changes around the starting composition.
Short narrative beatsBuild a focused 3–10 second action with a clear beginning, progression, and final visual payoff.

Prompt Guide

Refer to the starting frame as @Image1 and the optional ending frame as @Image2. First state what must remain consistent, then describe the movement and transformation in chronological order. Add camera direction, subject motion, environmental changes, lighting, pacing, and the desired finish. When an end frame is supplied, explain how the action should naturally bridge the two images instead of merely describing them separately.

{
  "prompt": "Keep the ancient tree and central composition from @Image1 recognizable. Begin in cold winter light as loose snow falls from the branches. The camera slowly pushes forward while the snow melts, green grass emerges, and pink blossoms open in a flowing magical time-lapse. Warm spring sunlight gradually replaces the blue light. Finish naturally on the fully blooming landscape shown in @Image2, with smooth cinematic motion and realistic depth.",
  "image": "https://example.com/winter-start.png",
  "end_image": "https://example.com/spring-end.png",
  "duration": 8
}

Technical Specs

PropertyDetails
Model IDkwaivgi/kling-video/3.0/omni/pro/image-to-video
Required inputsprompt, image
Start frameURL in image; maximum 10 MB, minimum 300 × 300 px, aspect ratio from 0.40 to 2.50
End frameOptional URL in end_image
Prompt lengthUp to 2,500 characters
Frame referencesUse @Image1 for the start frame and @Image2 for the end frame
Output duration3–10 whole seconds; default 5
OutputDownloadable MP4 video URL with optional content type
ExecutionAsynchronous

Related Models

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API
Unified Run API endpoint
https://api.sandbase.ai/v1/run
Model ID
kwaivgi/kling-video/3.0/omni/pro/image-to-video
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
  -X POST "https://api.sandbase.ai/v1/run" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "kwaivgi/kling-video/3.0/omni/pro/image-to-video",
  "image": "https://static.sandbase.ai/examples/kwaivgi/kling-video/omni/pro/image-to-video/input_image_0.png",
  "prompt": "Create a magical timelapse transition. The snow melts rapidly to reveal green grass, and the tree branches burst into bloom with pink flowers in real-time. The lighting shifts from cold winter light to warm spring sunshine. The camera pushes in slowly towards the tree. Disney-style magical transformation, cinematic, 8k.",
  "duration": 5,
  "end_image": "https://static.sandbase.ai/examples/kwaivgi/kling-video/omni/pro/image-to-video/input_end_image_1.png"
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
  status=$(printf '%s' "$result" | jq -r .status)
  case "$status" in completed|failed|timeout) break ;; esac
  sleep 2
  result=$(curl --fail-with-body --silent \
    -H "Authorization: Bearer $SANDBASE_API_KEY" \
    "https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"

Choose your model

Compare models

All language models
ModelContextInput / 1MOutput / 1MReleased
Kling 3.0 Omni Pro Image to VideoThis model
KwaiVGI		———Jul 3, 2026
Kling Video O3
KwaiVGI		———Jul 6, 2026
Kling Video V3
KwaiVGI		———Jul 6, 2026
Kling 3.0 Omni Pro Video Reference
KwaiVGI		———Jul 3, 2026
Kling 3.0 Omni Pro Video Edit
KwaiVGI		———Jul 3, 2026
Kling 3.0 Omni Pro Reference to Video
KwaiVGI		———Jul 3, 2026