Video Generationtextimage

Kling 2.5 Turbo

可灵 2.5 Turbo 视频生成，支持文生视频、首帧图生视频和首尾帧图生视频。

Input

Generation mode

Describe the video with text only, no images required.

Prompt

Reference image (optional)

PNG, JPG or WebP · you can also drag and drop a file here

Ready to generate

API Reference

POSThttps://api.token360.ai/v1/videos

# Step 1: Create video generation task
curl https://api.token360.ai/v1/videos \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
  "model": "kling-2.5-turbo",
  "prompt": "A cat walking across a room",
  "duration": 5,
  "cfg_scale": 0.5,
  "resolution": "720p",
  "aspect_ratio": "16:9",
  "generate_audio": false,
  "keep_original_sound": false,
  "character_orientation": "auto"
}'

# Step 2: Poll for completion (replace VIDEO_ID with the id from step 1)
curl https://api.token360.ai/v1/videos/VIDEO_ID \
  -H "Authorization: Bearer your-api-key"

API Documentation

Overview#

Kling 2.5 Turbo supports text-to-video, first-frame image-to-video, and first+last-frame image-to-video. Generic reference-image mode is not supported.

Text to video request#


curl -X POST https://api.token360.ai/v1/videos \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
    "model": "kling-2.5-turbo",
    "prompt": "A cinematic cat sprinting through a neon alley at night",
    "duration": 5,
    "aspect_ratio": "16:9",
    "mode": "std"
  }'

Image to video request#


curl -X POST https://api.token360.ai/v1/videos \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
    "model": "kling-2.5-turbo",
    "prompt": "The astronaut turns toward camera and smiles",
    "duration": 5,
    "aspect_ratio": "16:9",
    "mode": "std",
    "frame_images": [
      {"type": "image_url", "frame_type": "first_frame", "image_url": {"url": "https://example.com/first-frame.png"}}
    ]
  }'

Poll task status#


curl https://api.token360.ai/v1/videos/VIDEO_ID \
  -H "Authorization: Bearer your-api-key"