Kwaivgi Kling Video O1 Std Text To Video

Kwaivgi Kling Video O1 Std Text To Video

Playground

Kling Omni Video O1 (Standard) is Kuaishou’s first unified multi-modal video model with MVL (Multi-modal Visual Language) technology. Text-to-Video mode generates cinematic videos from text prompts with subject consistency, natural physics simulation, and precise semantic understanding. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.

Features

Kling Omni Video O1 is Kuaishou’s unified multi-modal video generation model, optimized for stable production use and cost efficiency. The Text-to-Video mode transforms natural language prompts into high-quality videos with coherent motion, accurate semantic understanding, and consistent visual output.

Why Kling Video O1 (Standard)

Unified Creative Engine

The model supports multiple video generation and editing workflows within a single system:

• Text-to-video generation
• Image-to-video transformation
• Reference-based video creation
• Video editing and modification
• Shot extension and scene continuation

Multi-Modal Visual Language (MVL)

The model interprets instructions through MVL, enabling understanding of:

• Natural language descriptions
• Visual context and references
• Subject identity and appearance
• Scene structure and motion dynamics

Subject Consistency

Maintains stable characters, objects, and scene attributes across frames, ensuring reliable and repeatable results suitable for production workflows.

Core Features

• Cinematic-quality video generation with natural motion
• Stable temporal consistency across the entire sequence
• Accurate semantic understanding of text prompts
• Support for multiple resolutions and output durations
• Standard optimization for balanced quality, speed, and cost

How to Use

1. Write Your Prompt Describe the scene, action, camera movement, and overall mood. > Example: “A young woman walking through a neon-lit Tokyo street at night, rain reflecting city lights, cinematic tracking shot”

2. Set Parameters Choose the desired duration, and aspect ratio.

3. Generate Submit the request and receive a coherent video generated from text.

Pricing

Billed based on the selected output duration. Pricing is optimized for standard production workloads.

Pro Tips

• Use clear and descriptive prompts
• Specify camera movement and framing for better motion quality
• Include lighting, environment, and atmosphere details
• Suitable for large-scale generation and cost-sensitive use cases

Kling O1 series models

• kwaivgi/kling-video-o1-std — Video Edit — Edit videos with natural-language instructions for precise, context-aware changes like object removal, scene adjustments, and style refinement while preserving motion consistency.

• kwaivgi/kling-video-o1-std — Reference to Video — Generate new videos guided by a reference video to match its style, identity, or motion patterns, ideal for consistent visual storytelling and content iteration.

• kwaivgi/kling-video-o1-std — Image to Video — Animate a single image into a high-quality video clip with smooth motion and coherent scene continuity, perfect for marketing creatives and social content.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "aspect_ratio": "16:9",
  "duration": 5
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/kwaivgi/kling-video-o1-std/text-to-video" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters