Kling V1.6 I2V Pro
Generate 5s videos in 1080p resolution from image
Features
Kling-v1.6-I2V-Pro is an advanced image-to-video generation model developed by the Kuaishou AI Team. Building upon the capabilities of the Kling AI platform, this model transforms static images into dynamic, high-quality videos, enabling users to create compelling visual narratives with ease.
Key Features
- Kling-V1.6-i2v-pro is an advanced image-to-video generation model designed to transform static images into high-quality, dynamic videos. This model builds on the capabilities of its predecessor, Kling V1.6, with significant improvements in visual quality, motion dynamics, and semantic understanding. Key features include:
- High-Quality Video Output: Both models generate 5-second videos in 720p and 1080p resolution with vivid details and cinematic quality.
- Enhanced Motion Rendering: Utilizes advanced dynamic rendering techniques to create smooth and natural movements, making the generated videos more engaging and visually appealing.
- Improved Semantic Understanding: Excels in interpreting complex user prompts to generate coherent and dynamic scenes that align closely with user expectations.
- Physical Realism: Simulates realistic physical properties and movements, ensuring the generated videos adhere to natural laws and appear lifelike.
- Fast Processing: Optimized for efficient generation, allowing users to create high-quality videos quickly.
- Customizable Parameters: Offers adjustable settings such as duration, quality, and style, providing users with greater control over the final output.
ComfyUI
kwaivgi/kling-v1.6-i2v-pro is also available on ComfyUI, providing local inference capabilities through a node-based workflow, ensuring flexible and efficient image generation on your system.
Limitations
- Creative Content Focus: Designed primarily for creative video synthesis; not intended for generating factually accurate or reliable content.
- Input Sensitivity: The quality and consistency of generated videos depend significantly on the quality of the input image; subtle variations may lead to output variability.
- Resource Requirements: While optimized for performance, generating high-resolution videos with complex simulations may require substantial computational resources.
Out-of-Scope Use
The model and its derivatives may not be used in any way that violates applicable national, federal, state, local, or international law or regulation, including but not limited to:
- Exploiting, harming, or attempting to exploit or harm minors, including solicitation, creation, acquisition, or dissemination of child exploitative content.
- Generating or disseminating verifiably false information with the intent to harm others.
- Creating or distributing personal identifiable information that could be used to harm an individual.
- Harassing, abusing, threatening, stalking, or bullying individuals or groups.
- Producing non-consensual nudity or illegal pornographic content.
- Making fully automated decisions that adversely affect an individual’s legal rights or create binding obligations.
- Facilitating large-scale disinformation campaigns.
Accelerated Inference
Our accelerated inference approach leverages advanced optimization technology from WavespeedAI. This innovative fusion technique significantly reduces computational overhead and latency, enabling rapid image generation without compromising quality. The entire system is designed to efficiently handle large-scale inference tasks while ensuring that real-time applications achieve an optimal balance between speed and accuracy. For further details, please refer to the blog post.
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 ${WAVESPEED_API_KEY}" \
--data-raw '{
"image": "https://d2g64w682n9w0w.cloudfront.net/media/images/1747220408880912820_13ZWSPLJ.jpg",
"prompt": "A girl falling slowly underwater, calm and serene facial expression, light and shadow dancing on her face. She gently raises both arms, hair flowing softly in water, high-quality visuals, slow motion, cinematic lighting",
"guidance_scale": 0.5,
"duration": "5"
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
Parameter | Type | Required | Default | Range | Description |
---|---|---|---|---|---|
image | string | Yes | https://d2g64w682n9w0w.cloudfront.net/media/images/1747220408880912820_13ZWSPLJ.jpg | - | 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. |
prompt | string | No | 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 | - | Text prompt for generation; Positive text prompt; Cannot exceed 2500 characters |
negative_prompt | string | No | - | - | Negative text prompt; Cannot exceed 2500 characters |
guidance_scale | number | No | 0.5 | 0.00 ~ 1.00 | Flexibility in video generation; The higher the value, the lower the model’s degree of flexibility, and the stronger the relevance to the user’s prompt. |
duration | string | No | 5 | 5, 10 | Generate video duration length 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 Query Parameters
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 |
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 |