Kwaivgi Kling V2.5 Turbo Std Image To Video

Kwaivgi Kling V2.5 Turbo Std Image To Video

Playground

Try it on WaveSpeedAI!

Kling 2.5 Turbo Std delivers image-to-video with fluid motion, cinematic visuals, and precise prompts at 25% lower pricing vs 2.1 Std. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Kling V2.5 Turbo Standard is a high-performance image-to-video generation model optimized for speed, quality, and affordability. It transforms a single image and a short prompt into smooth, cinematic video clips that preserve the original style, lighting, and emotion β€” all at a lower cost than previous versions.


🌟 Model Highlights

  • πŸ’° Ultra Cost-Effective Delivers higher visual quality at a 25% lower price compared with Kling V2.1 Standard. The model provides stunning realism while significantly reducing generation costs.

  • 🏒 B2B Early Access Exclusively launched for enterprise clients through an invite-only program. The model will be publicly available on Kling Web/App around November, giving B-end users an early advantage and extended testing window.

  • 🎬 Pro-Level Visual Quality Although output resolution is 720p, the model’s refined dynamics and motion synthesis ensure rich details, clean motion, and stable lighting that meet the needs of most video generation scenarios.

  • ⚑ Fast Inference Built with optimized pipelines for rapid generation β€” ideal for high-volume creative workflows.

  • 🧠 Strong Text Comprehension Matches the Kling 2.5 Turbo Pro version in prompt understanding and narrative coherence, producing well-timed, semantically accurate motion.


βš™οΈ Capabilities

  • Input: Image + text prompt
  • Output: 720p video
  • Supported Durations: 5s / 10s
  • Use Cases: Marketing videos, storyboards, explainers, short-form content

πŸ’° Pricing

DurationPrice (USD)
5s$0.21
10s$0.42

🧩 How to Use

  1. Write your prompt β€” describe the subject, camera movement, and atmosphere.
  2. Upload a reference image β€” defines composition and color tone.
  3. Set duration β€” choose 5s or 10s depending on your creative need.
  4. Adjust guidance_scale β€” higher values increase prompt adherence.
  5. Run generation β€” fast inference delivers results within seconds.
  6. Review & iterate β€” tweak prompts or seeds for variations.

πŸ’‘ Ideal For

  • Marketing & Brand Teams β€” Generate short ads or motion design clips quickly.
  • Content Creators & YouTubers β€” Produce narrative motion from static art.
  • Studios & Production Houses β€” Use as a previsualization tool for scene planning.
  • Education & Explainers β€” Turn diagrams or slides into dynamic videos.

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",
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "guidance_scale": 0.5,
  "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-v2.5-turbo-std/image-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

ParameterTypeRequiredDefaultRangeDescription
promptstringYes-The positive prompt for the generation.
imagestringYes-First frame of the video; Supported image formats include.jpg/.jpeg/.png; The image file size cannot exceed 10MB, and the image resolution should not be less than 300*300px, and the aspect ratio of the image should be between 1:2.5 ~ 2.5:1.
negative_promptstringNo-The negative prompt for the generation.
guidance_scalenumberNo0.50 ~ 1The guidance scale to use for the generation.
durationintegerNo55, 10The duration of the generated media in seconds.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., β€œsuccess”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayOutput values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., β€œ2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., β€œsuccess”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction
data.modelstringModel ID used for the prediction
data.outputsarray<string | object>Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model.
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to poll for the prediction result
data.statusstringStatus: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
Β© 2026 WaveSpeedAI. All rights reserved.