Kling v1.6 i2v Pro boosts image-to-video output 195% over Kling 1.5 with improved prompt understanding, physics and visual effects for realistic output. Ready-to-use REST inference API, no coldstarts, affordable pricing.
Ocioso
$0.45por execução·~22 / $10
ExemplosVer todos
a portrait photo of a woman underwater with flowing hair
cat jump
A girl falling slowly underwater, calm and serene facial expression, light and shadow dancing on her face. She gently raises both arms, hair flowing softly in water, high-quality visuals, slow motion, cinematic lighting
An elderly man with a kind smile reading a book by a fireplace, the flames casting a warm glow on his face, a loyal dog sleeping at his feet.
A mischievous kitten playing with a ball of yarn, its fur fluffy and white, in a cozy living room with sunlight streaming through the window.
A young woman in a flowing white dress stands on a cliff overlooking a vast ocean, with the sun setting behind her, golden hour.
A futuristic cityscape with flying cars and towering skyscrapers, bathed in a purple and blue glow, cyberpunk aesthetic.
A single, vibrant red rose slowly unfurling its petals in time-lapse, dew drops glistening on its velvety surface, elegant.
An astronaut floating weightlessly inside a dimly lit spaceship, looking out at a swirling nebula through a large viewport, awe-inspiring.
A teenage boy stands under a bus stop shelter on a rainy afternoon, droplets running down the glass beside him, school bag slung over one shoulder, cars passing in the background, a soft melancholic mood filling the scene.
Modelos relacionados
README
Kling v1.6 I2V Pro — kwaivgi/kling-v1.6-i2v-pro
Kling v1.6 I2V Pro is an image-to-video (I2V) model that turns a reference image into a short, coherent video clip driven by your prompt. It’s designed for stable motion, strong subject consistency, and cinematic camera control, making it a solid choice for product shots, character shots, and ad-style sequences.
What it’s good at
- Image-to-Video (I2V): animate a single input image into a short clip
- Prompt-driven motion: control action, pacing, and camera movement via text
- Subject consistency: keep the main subject recognizable across frames
- Cinematic framing: works well with “director-style” prompts (shots, lenses, camera moves)
Inputs
- Prompt (required): describe subject, motion, environment, lighting, and camera
- Negative prompt (optional): specify what to avoid (e.g., blur, jitter, distortion)
- Image (required): the starting reference image
- End image (optional): guide the clip to land closer to a target final frame
Key parameters
-
Duration: 5s (and other supported durations depending on the deployment)
-
Guidance scale: controls how strictly the generation follows the prompt
-
Lower: more natural/loose motion
-
Higher: stronger prompt adherence (can reduce naturalness if pushed too high)
Prompting tips (I2V)
- Write like a director: Subject + Action + Scene + Camera + Style
- Add motion verbs and pacing words: turns, steps forward, spins, slowly, rapidly
- Specify the camera: close-up, wide shot, dolly-in, orbit, handheld, slow pan
- Use the end image when you need a clear “arrival” (pose change, composition shift, scene progression)
- Keep negative prompts practical: blurry, jittery, flicker, distorted, low quality, inconsistent motion
Common use cases
- Ad creatives: animate a product/portrait image into multiple short variants fast
- Character motion tests: generate subtle facial/body motion and camera movement
- Scene continuation: use an end image to guide story progression within a short clip
- Style exploration: try different cinematography directions without re-shooting assets
Pricing
| Mode | Duration | Price per video |
|---|---|---|
| I2V Pro | 5s | $0.45 |
Kling v1.6 I2v Pro API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/kwaivgi/kling-v1.6-i2v-pro with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Kling v1.6 I2v Pro below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/kwaivgi/kling-v1.6-i2v-pro" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"negative_prompt": "blurry, low quality, distorted",
"guidance_scale": 0.5,
"duration": 5
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("kwaivgi/kling-v1.6-i2v-pro", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"negative_prompt": "blurry, low quality, distorted",
"guidance_scale": 0.5,
"duration": 5
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"kwaivgi/kling-v1.6-i2v-pro",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"negative_prompt": "blurry, low quality, distorted",
"guidance_scale": 0.5,
"duration": 5
}
)
print(output["outputs"][0]) # → URL of the generated outputKling v1.6 I2v Pro API — Frequently asked questions
What is the Kling v1.6 I2v Pro API?
Kling v1.6 I2v Pro is a Kuaishou model for video generation from images, exposed as a REST API on WaveSpeedAI. Kling v1.6 i2v Pro boosts image-to-video output 195% over Kling 1.5 with improved prompt understanding, physics and visual effects for realistic output. Ready-to-use REST inference API, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Kling v1.6 I2v Pro API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/kwaivgi/kwaivgi-kling-v1.6-i2v-pro.
How much does Kling v1.6 I2v Pro cost per run?
Kling v1.6 I2v Pro starts at $0.45 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does Kling v1.6 I2v Pro accept?
Key inputs: `prompt`, `image`, `duration`, `guidance_scale`, `negative_prompt`, `end_image`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/kwaivgi/kwaivgi-kling-v1.6-i2v-pro.
How long does Kling v1.6 I2v Pro take to generate?
Average end-to-end generation time on WaveSpeedAI is around 441 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Kling v1.6 I2v Pro outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (Kuaishou). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.