Kling V2.1 Image-to-Video
Video
Kling V2.1 Image-to-Video
POST
Kling V2.1 Image-to-Video
Kling V2.1 is the latest generation AI-powered image-to-video model from the Kuaishou team, capable of generating high-quality, cinematic short videos from a single image or text prompt. Compared to Kling 2.0, version 2.1 features significant breakthroughs in motion smoothness, visual consistency, and prompt comprehension.
Request Headers
Enum:
application/jsonBearer authentication format: Bearer {{API Key}}.
Request Body
First frame image for the video. Supported image formats include
.jpg, .jpeg, .png. Image file size must not exceed 10MB, with a minimum resolution of 300x300 pixels.Positive text prompt for video generation. Must not exceed 2500 characters.
Video generation mode.Supported:
Standard: Fast generation, lower cost, produces 720p video.Professional: High quality, higher cost, produces 1080p video.
Standard.Duration of the generated video (in seconds).Possible values:
5, 10Guidance scale parameter that controls how closely the generated content adheres to the prompt.Range: 0 to 1
Step: 0.01
Step: 0.01
Negative prompt to specify content to avoid in the generation. Must not exceed 2500 characters.
Response
The task_id of the async task. Use the task_id to call the Get Async Task Result API to retrieve the generated result.