Kling v2.1 by Kuaishou makes 5–10s 720p/1080p videos from an image or text prompt with improved motion fidelity and visual coherence. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.25per run·~40 / $10
ExamplesView all
A cyberpunk girl walking through neon-lit alleyways, rain falling, close-up of her eyes, camera pans to her silhouette, smoke in the background, futuristic music vibe
A fantasy knight standing on a cliff at sunset, cape fluttering, camera zooms out to reveal vast mountain range, slow motion, golden hour lighting
The man casually adjusts his sunglasses and looks to the side, a slight breeze moves his jacket, light reflections flicker across the car surface, subtle movement in the background crowd
She turns slightly to face the lake, her braid sways gently, golden light shimmers on the water, a bird flies in the background, soft ambient motion
The petals fall slowly around her, she gently raises the umbrella and tilts her head, her sleeves sway with the wind, a poetic moment frozen in gentle motion
Her eyes scan the surroundings as her armor emits a faint pulse, neon lights reflect off puddles, raindrops fall slowly in the background, subtle turn of her head
A forest elf girl with glowing wings, sitting on a mossy rock surrounded by fireflies, magical forest atmosphere, soft lighting.Her wings shimmer with delicate motion, fireflies dance around her, she turns to smile softly, foliage sways slightly as ambient light flickers
A female warrior with silver armor and a sword, standing on a mountain peak, dramatic clouds behind her, fantasy style, cinematic lighting.Her cape flutters in the mountain wind, she lifts her sword slightly, the clouds swirl with tension, her hair flowing dramatically as she faces the horizon
A young woman traveler with a backpack standing on a train platform at sunrise, wearing casual clothes, holding a camera.She glances at her watch, then looks up toward the arriving train, her hair sways gently in the morning breeze, a soft lens flare from the rising sun
A female astronaut in a sleek space suit, standing in front of a large observation window showing a galaxy view, cold lighting.The stars slowly drift across the window, her eyes track the movement, slight motion in her suit's light indicators, a sense of vastness and quiet tension
A teenage girl painting on a canvas in a cozy studio, wearing an oversized shirt with paint stains, warm lighting from a side window.She dips her brush and continues to paint, her hand moving with precision, dust particles dance in the light beam, canvas shimmers with evolving color
She pauses and lifts the hat slightly, the wheat sways with the morning breeze, light glints off dewdrops, a soft smile forms on her face
She exhales slowly and bows slightly, her costume rustling, the spotlight dims subtly, audience shadows shift as the scene transitions
The wind lifts the edge of her cape as she slowly draws her sword, clouds shift subtly in the sky, the banner behind her flutters with tension
The wind lifts her hair gently, she clicks the camera shutter with a smile, a flock of birds passes in the sky, the rooftop catches soft fading light
Related Models
README
Kling v2.1
Kling v2.1 is an AI video generation model developed by KlingAI (Kuaishou). It is purpose-built for creators, artists, and production teams seeking fast, realistic video generation from image and text prompts. Ideal for rapid prototyping, rough drafts, and creative iteration, it balances performance with affordability—while maintaining high-quality motion dynamics and visual coherence.
🔍 Overview
Kling 2.1 leverages 3D spatiotemporal attention, advanced motion synthesis, and cinematic camera simulation to transform static inputs into dynamic, photorealistic video clips. The i2v-standard variant provides a lightweight version for scalable generation tasks without sacrificing essential quality.
✨ Key Features
-
Smooth Motion
-
Advanced stabilization techniques ensure jitter-free movement across frames, even during complex sequences.
-
High-Fidelity Rendering
-
Realistic modeling of skin, fluids, materials, and reflections to preserve physical consistency.
-
Prompt Understanding
-
Enhanced context-aware interpretation of complex actions, camera directives, and stylistic cues.
-
Camera Control
-
Supports cinematic moves like dolly zooms, panning, and programmable motion paths for enhanced visual storytelling.
🎯 Use Cases
-
Short-Form Video Production
-
Generate fast and engaging clips for TikTok, YouTube Shorts, Instagram Reels, etc.
-
Storyboarding and Previsualization
-
Create visual drafts for films, ads, or animation projects with dynamic composition.
-
Promotional Content
-
High-resolution marketing videos for commercial brands or product showcases.
-
Artistic Video Creation
-
Stylized, experimental outputs suitable for NFTs, video art, and immersive storytelling.
-
Game and Simulation Previews
-
Generate scene previews for virtual environments and narrative cutscenes in game development.
Kling v2.1 I2v Standard API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/kwaivgi/kling-v2.1-i2v-standard 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 v2.1 I2v Standard below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/kwaivgi/kling-v2.1-i2v-standard" \
-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-v2.1-i2v-standard", {
"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-v2.1-i2v-standard",
{
"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 v2.1 I2v Standard API — Frequently asked questions
What is the Kling v2.1 I2v Standard API?
Kling v2.1 I2v Standard is a Kuaishou model for video generation from images, exposed as a REST API on WaveSpeedAI. Kling v2.1 by Kuaishou makes 5–10s 720p/1080p videos from an image or text prompt with improved motion fidelity and visual coherence. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Kling v2.1 I2v Standard 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-v2.1-i2v-standard.
How much does Kling v2.1 I2v Standard cost per run?
Kling v2.1 I2v Standard starts at $0.25 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 v2.1 I2v Standard accept?
Key inputs: `prompt`, `image`, `duration`, `guidance_scale`, `negative_prompt`. 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-v2.1-i2v-standard.
How long does Kling v2.1 I2v Standard take to generate?
Average end-to-end generation time on WaveSpeedAI is around 66 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 v2.1 I2v Standard 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.