Kwaivgi Kling Video O3 Std Reference To Video

Kwaivgi Kling Video O3 Std Reference To Video

Playground

Kling Omni Video O3 (Standard) Reference-to-Video generates creative videos using character, prop, or scene references from multiple viewpoints. Extracts subject features and creates new video content while maintaining identity consistency across frames. Supports audio generation. Ready-to-use REST API, best performance, no cold starts, affordable pricing.

Features

Kling Omni Video O3 — Reference-to-Video (Standard)

Kling Omni Video O3 (Standard) is Kuaishou’s advanced unified multi-modal video model, optimized for production workloads. The Reference-to-Video mode creates new video content based on subject references — maintaining character, prop, and scene identity while generating entirely new creative scenarios. Supports optional audio generation.

Key Capabilities

Multi-Reference Subject Creation

Build subjects from multiple reference viewpoints:

• Extract features from character, prop, or scene images
• Maintain consistent identity in generated videos
• Create new scenarios with familiar subjects

Subject Consistency Technology

Advanced feature extraction ensures:

• Stable character appearance across all frames
• Consistent clothing, accessories, and props
• Maintained facial features and expressions
• Coherent scene elements and backgrounds

Creative Freedom

Generate entirely new content while preserving identity:

• New poses and actions
• Different scenes and environments
• Various camera angles and movements
• Fresh creative scenarios

Audio Support

Optionally generate synchronized audio or keep original sound from reference videos.

Core Features

• Identity Lock — Subject features remain consistent throughout video
• Multi-Angle Support — Use references from various viewpoints
• Scene Flexibility — Place subjects in new environments
• Motion Control — Guide actions with text prompts
• Audio Options — Keep original sound or generate new audio
• Cost Optimized — Standard tier for production workloads

How to Use

1. Upload Reference Images/Video Provide one or more images of your subject (character, object, or scene), or a reference video.

2. Describe the Scenario Write a prompt for the new video content.

   Example: “The character walking through a futuristic city at night, neon lights reflecting on wet streets”

3. Set Parameters Choose duration (3-15s), aspect ratio, and audio options.

4. Generate Receive video with your subject in the new scenario.

Pricing

$0.084/s for image reference only; $0.126/s when using video reference (1.5x multiplier).

Pro Tips

• Use multiple reference angles for better identity capture
• Provide clear, high-resolution reference images
• Describe actions and environments clearly in prompts
• Works best for characters, products, and distinct objects

Note

• If the input reference parameters include a video, then the number of reference images that can be entered will be reduced to 4.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/kwaivgi/kling-video-o3-std/reference-to-video" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "keep_original_sound": true,
    "sound": false,
    "aspect_ratio": "16:9",
    "duration": 5
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"