About Kling O1 - Image to Video
Kling O1 - Image to Video is a diffusion-based multimodal video generation model designed for turning images (optionally combined with text and other visual references) into short, coherent video clips.
It excels in image-to-video generation where a single image or a small set of reference images is transformed into cinematic clips with stable characters, controlled motion, and consistent environments, while respecting prompts for style, mood, and camera movement.
Some other noteworthy features of Kling O1 - Image to Video include support for multiple image references (up to 7 in some workflows) to refine character identity and scene details, and controls such as start/end frame specification and motion/camera behavior guidance to achieve smoother, more intentional transitions and storytelling shots.
Ready to build with Kling O1 - Image to Video?
Try Kling O1 - Image to Video in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/videos/generate \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "kling-video-o1-image-to-video",
"prompt": "Zoom into the ox, while it is walking forward on the road, change the season from winter to summer as you zoom in, cinematic",
"input_image": "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/images/ox_zoom_out_1926_1076.png",
"duration": 5
}'Request parameters
Every field Kling O1 - Image to Video accepts in the request body. See the API reference for response formats.
https://hub.oxen.ai/api/ai/videos/generate| Field | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes | — | Text description of what you want to generate, or the instruction on how to edit the given image. |
input_image | stringuri | Yes | — | Image to use as reference. Must be jpeg, png, gif, or webp. |
tail_image_url | stringuri | No | — | Image to use as reference. Must be jpeg, png, gif, or webp. |
duration | integer | No | 5 | Range: 5 – 10 |