Kwaivgi Kling V1.6 Multi I2V Standard

Kwaivgi Kling V1.6 Multi I2V Standard

Playground

Kling v1.6 Image-to-Video delivers 195% better results than Kling 1.5, with better prompt understanding, physics, and visual effects. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Transform multiple reference images into cinematic videos with Kling V1.6. This powerful image-to-video model accepts up to 4 reference images, enabling more complex scene composition, character consistency, and creative control — perfect for fashion editorials, product showcases, and storytelling content.

Why It Looks Great

• Multi-image input: Use up to 4 reference images for richer scene composition and better consistency.
• Cinematic motion: Creates smooth, professional-quality movement with dramatic flair.
• Negative prompt support: Exclude unwanted elements for precise control over the output.
• Flexible duration: Generate 5-second or 10-second videos.
• Multiple aspect ratios: Square (1:1), landscape (16:9), or portrait (9:16) formats.
• Prompt Enhancer: Built-in tool to refine and expand your motion descriptions.
• Safety Checker: Optional content filtering for appropriate output.

Parameters

How to Use

1. Write your prompt — describe the motion, camera work, and atmosphere in detail.
2. Use Prompt Enhancer (optional) — click to automatically enrich your description.
3. Add negative prompt (optional) — specify elements to exclude.
4. Upload reference images — add up to 4 images using the ”+ Add Item” button.
5. Set duration — choose 5 or 10 seconds.
6. Select aspect ratio — pick the format that fits your use case.
7. Run — click the button to generate.
8. Download — preview and save your video.

Pricing

Per 5-second billing based on duration.

Volume Examples

Best Use Cases

• Fashion Editorials — Create runway-style videos with dramatic fabric movement and cinematic lighting.
• Product Showcases — Animate product images with dynamic camera movements.
• Character Animation — Use multiple reference images for consistent character appearance.
• Storytelling — Combine multiple scene elements into cohesive video narratives.
• Social Media Content — Generate eye-catching videos optimized for different platforms.

Example Prompts

• “Model in a flowing silk gown standing on top of a sand dune, golden sunset light illuminating the fabric, camera circling to capture the dress fluttering dramatically in the wind, high-contrast editorial style”
• “Slow camera push in, hair moving gently in the breeze, warm golden hour lighting”
• “Product rotating smoothly on display, studio lighting creating elegant reflections”
• “Dramatic camera orbit around the subject, fabric flowing in slow motion”
• “Cinematic dolly shot revealing the full scene, atmospheric dust particles in the light”

Multi-Image Tips

Pro Tips for Best Results

• Use multiple images when you need consistency across different elements (character + background + props).
• Include cinematic language: “camera circling”, “dolly shot”, “slow motion”, “dramatic lighting”.
• Describe both subject motion and camera movement for more dynamic results.
• Use negative prompts to avoid “blur”, “distortion”, “static”, “jitter”.
• Match aspect ratio to your platform: 1:1 for Instagram, 16:9 for YouTube, 9:16 for TikTok/Reels.
• Start with 5-second videos to test your concept before generating 10-second versions.

Notes

• If using URLs for images, ensure they are publicly accessible. Preview thumbnails confirm successful loading.
• Processing time scales with duration — 10-second videos take longer.
• Enable Safety Checker for content that will be publicly shared.
• Reference images influence style and composition — choose high-quality sources.

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",
  "images": [
    "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
  ],
  "duration": 5,
  "aspect_ratio": "1:1"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/kwaivgi/kling-v1.6-multi-i2v-standard" \
  -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