Kwaivgi Kling V1.6 I2V Pro

Playground

Kling v1.6 i2v Pro boosts image-to-video output 195% over Kling 1.5 with improved prompt understanding, physics and visual effects for realistic output. Ready-to-use REST inference API, no coldstarts, affordable pricing.

Features

Kling v1.6 I2V Pro — kwaivgi/kling-v1.6-i2v-pro

Kling v1.6 I2V Pro is an image-to-video (I2V) model that turns a reference image into a short, coherent video clip driven by your prompt. It’s designed for stable motion, strong subject consistency, and cinematic camera control, making it a solid choice for product shots, character shots, and ad-style sequences.

What it’s good at

Image-to-Video (I2V): animate a single input image into a short clip
Prompt-driven motion: control action, pacing, and camera movement via text
Subject consistency: keep the main subject recognizable across frames
Cinematic framing: works well with “director-style” prompts (shots, lenses, camera moves)

Inputs

Prompt (required): describe subject, motion, environment, lighting, and camera
Negative prompt (optional): specify what to avoid (e.g., blur, jitter, distortion)
Image (required): the starting reference image
End image (optional): guide the clip to land closer to a target final frame

Key parameters

Duration: 5s (and other supported durations depending on the deployment)
Guidance scale: controls how strictly the generation follows the prompt
- Lower: more natural/loose motion
- Higher: stronger prompt adherence (can reduce naturalness if pushed too high)

Prompting tips (I2V)

Write like a director: Subject + Action + Scene + Camera + Style
Add motion verbs and pacing words: turns, steps forward, spins, slowly, rapidly
Specify the camera: close-up, wide shot, dolly-in, orbit, handheld, slow pan
Use the end image when you need a clear “arrival” (pose change, composition shift, scene progression)
Keep negative prompts practical: blurry, jittery, flicker, distorted, low quality, inconsistent motion

Common use cases

Ad creatives: animate a product/portrait image into multiple short variants fast
Character motion tests: generate subtle facial/body motion and camera movement
Scene continuation: use an end image to guide story progression within a short clip
Style exploration: try different cinematography directions without re-shooting assets

Pricing

Mode	Duration	Price per video
I2V Pro	5s	$0.45

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 '{
    "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

Parameter	Type	Required	Default	Range	Description
prompt	string	Yes		-	The positive prompt for the generation. max length 2500
negative_prompt	string	No		-	The negative prompt for the generation.
image	string	Yes		-	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_image	string	No	-	-	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_scale	number	No	0.5	0.00 ~ 1.00	The guidance scale to use for the generation.
duration	integer	No	5	5, 10	The duration of the generated media in seconds.

Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data.id	string	Unique identifier for the prediction, Task Id
data.model	string	Model ID used for the prediction
data.outputs	array	Array of URLs to the generated content (empty when status is not `completed`)
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.has_nsfw_contents	array	Array of boolean values indicating NSFW detection for each output
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Result Request Parameters

Parameter	Type	Required	Default	Description
id	string	Yes	-	Task ID

Result Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data	object	The prediction data object containing all details
data.id	string	Unique identifier for the prediction, the ID of the prediction to get
data.model	string	Model ID used for the prediction
data.outputs	string	Array of URLs to the generated content (empty when status is not completed).
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Kwaivgi Kling V1 Tts Kwaivgi Kling V1.6 I2V Standard