WaveSpeedAI APIKwaivgi Kling V1.6 I2v Pro

Kwaivgi Kling V1.6 I2V Pro

Kwaivgi Kling V1.6 I2V Pro

Playground

Try it on WavespeedAI!

Kling AI released its latest 1.6 model on Dec 19, 2024. The new model boasts a remarkable 195% improvement in image-to-video generation capabilities compared to Kling 1.5, with a better understanding of prompts and enhanced physics and visual effects, setting a new benchmark in AI video creation.

Features

Kling AI 1.6 Key Features

  • Improved prompt adherence
    Delivers more precise and fitting responses to user instructions, especially for motion, camera angles, and sequential movements.

  • Upgraded motion dynamics
    Produces more natural and lifelike movements and facial expressions, making character actions fluid and realistic.

  • Enhanced image-to-video quality
    Offers superior color rendering, detailed visuals, realistic lighting and shadows, and consistent style for refined, high-quality videos.

  • Dual mode approach
    Supports both Standard mode for quick video creation and Professional mode for advanced customization and higher-quality production.


Improved Prompt Adherence

Kling 1.6 understands user prompts more intelligently, ensuring dynamic and consistent results aligned with expectations.

Sample:
Original image: girl riding broom
Prompt: Create an anime-style scene of a girl riding a broom in the sky with a black cat. Zoom in to a close-up of the girl’s face as she looks ahead with curiosity.


Upgraded Motion Dynamics

Delivers the most realistic human movements and facial expressions, from jumping and punching to subtle gestures, with fluidity almost indistinguishable from real life.

Sample:
Original image: kung fu master
Prompt: A Kung Fu master throws a punch, and the air behind him swirls into the shape of a dragon.


Enhanced Image-to-Video Quality

Features dynamic color rendering, detailed aesthetics, realistic lighting and shadows, and style consistency, producing visually impactful and polished videos.

Sample:
Original image: mechanical wolf
Prompt: A mechanical wolf rises slowly, spreading its limbs smoothly. The camera moves upward as its blue eyes narrow slightly. Neon lights flicker in the background, creating a mysterious futuristic atmosphere.


Dual Model Support

  • Standard mode: Quick and easy AI video creation.
  • Professional mode: Advanced customization for higher-quality, creative video production.

No Extra Costs

All new features and improvements in Kling 1.6 are available to users at no additional cost.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/kwaivgi/kling-v1.6-i2v-pro" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "prompt": "A girl falling slowly underwater, calm and serene facial expression, light and shadow dancing on her face. She gently raises both arms, hair flowing softly in water, high-quality visuals, slow motion, cinematic lighting",
    "negative_prompt": "blur, distort, and low quality",
    "image": "https://d3gnftk2yhz9lr.wavespeed.ai/media/images/1747220408880912820_13ZWSPLJ.jpg",
    "guidance_scale": 0.5,
    "duration": "5"
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
promptstringYes-Text prompt for generation; Positive text prompt; Cannot exceed 2500 characters.
negative_promptstringNo-Negative text prompt; Cannot exceed 2500 characters.
imagestringYes-First frame of the video; Supported image formats include.jpg/.jpeg/.png; The image file size cannot exceed 10MB, and the image resolution should not be less than 300*300px, and the aspect ratio of the image should be between 1:2.5 ~ 2.5:1.
end_imagestringNo--Tail frame of the video; Supported image formats include.jpg/.jpeg/.png; The image file size cannot exceed 10MB, and the image resolution should not be less than 300*300px.
guidance_scalenumberNo0.50.00 ~ 1.00The guidance scale to use for the generation.
durationstringNo55, 10The duration of the generated media in seconds.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayArray of URLs to the generated content (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.has_nsfw_contentsarrayArray of boolean values indicating NSFW detection for each output
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Query Parameters

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction, the ID of the prediction to get
data.modelstringModel ID used for the prediction
data.outputsarrayArray of URLs to the generated content (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.has_nsfw_contentsarrayArray of boolean values indicating NSFW detection for each output
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2025 WaveSpeedAI. All rights reserved.