About Kling O1 - Reference to Video
Kling O1 - Reference to Video is a multimodal video generation model designed for reference-guided video synthesis. It excels in transforming reference videos or images into new sequences while preserving motion dynamics, camera movements, and visual styles for consistent outputs.
Some other noteworthy features of Kling O1 - Reference to Video include image-to-video transformations, multi-reference image conditioning (up to 7 images), scene extension with continuity, and support for start/end frames or keyframes.
Ready to build with Kling O1 - Reference to Video?
Try Kling O1 - Reference 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.
bash
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-reference-to-video",
"prompt": "@Element1 flies into the scene and lands on the table next to the ox in @Image1",
"input_image": [
"https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/images/daily_moo.png"
],
"elements": [
{
"frontal_image_url": "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/images/red_bird.png",
"reference_image_urls": [
"https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/images/red_bird_side.png"
]
}
],
"aspect_ratio": "16:9",
"duration": 5
}'