Kling Text-to-Video
This series supports OpenAI video generation formats (see the link Video generation Sora compatible formats).
Use the Kling model to generate videos from text descriptions.
Supported models: kling-v1, kling-v1-5, etc.
Authorizations
Use Bearer Token authentication.
Format: Authorization: Bearer sk-xxxxxx
Body
Video generation request
Model/Style ID
"kling-v1"
Text description prompt
"宇航员站起身走了"
Image Input (URL or Base64)
"https://example.com/image.jpg"
Video duration (seconds)
5
Video width
1280
Video height
720
Video Frame Rate
30
Random Seed
20231234
Number of videos generated
1
Response Format
"url"
User ID
"user-1234"
Extended parameters (such as negative_prompt, style, quality_level, etc.)
