Token360
登录注册
Video Generationtextimagevideo

Kling 3.0 Omni

Kling Video 3.0 Omni 是可灵的原生多模态视频模型，支持文生视频、图生视频、参考视频、多镜头叙事与原生音频生成，最长支持 15 秒视频。

输入

生成方式

仅使用文本描述生成视频，无需上传图片。

参考图（可选）

支持 JPG/JPEG、PNG · 可拖拽上传

支持 JPG/JPEG、PNG · 可拖拽上传
Duration
315
Shot type
Watermark
Multi shot
Aspect ratio
Generate audio
准备开始生成准备开始生成

API 参考

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-3.0-omni",
  "prompt": "A cat walking across a room",
  "duration": 5,
  "shot_type": "customize",
  "watermark": false,
  "aspect_ratio": "16:9",
  "generate_audio": false,
  "keep_original_sound": false
}'

# 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 文档

Overview#

Kling Video 3.0 Omni is a native multimodal video model with text-to-video, image-to-video, reference-video, multi-shot storytelling, and native audio generation. The official release supports videos up to 15 seconds.

References#