Kwaivgi Kling V2.1 I2V Standard

Playground

Kling v2.1 is the latest evolution of Kuaishou’s AI-powered video‑generation model, designed to seamlessly create short, cinematic‑quality clips (typically 5–10 s at 720p or 1080p) from a single image or a text prompt. It represents a major leap forward from Kling 2.0, emphasizing motion fidelity, visual coherence, and prompt accuracy.

Features

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.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/kwaivgi/kling-v2.1-i2v-standard" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "prompt": "In a sky filled with swirling clouds and patches of bright sunlight, a fighter jet pilot expertly performs high-speed maneuvers. As the pilot spots an incoming threat, they swiftly execute a barrel roll to evade it. The jet's engines roar as it slices through the air, leaving a trail of contrails behind. ",
    "negative_prompt": "blur, distort, and low quality",
    "image": "https://d3gnftk2yhz9lr.wavespeed.ai/media/images/1749521540283047966_dqzyvrnl.jpeg",
    "guidance_scale": 0.5,
    "duration": "5"
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

Parameter	Type	Required	Default	Range	Description
prompt	string	Yes		-	Text prompt for generation; Positive text prompt; Cannot exceed 2500 characters.
negative_prompt	string	No		-	Negative text prompt; Cannot exceed 2500 characters.
image	string	Yes		-	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.
guidance_scale	number	No	0.5	0.00 ~ 1.00	The guidance scale to use for the generation.
duration	string	No	5	5, 10	The duration of the generated media in seconds.

Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data.id	string	Unique identifier for the prediction, Task Id
data.model	string	Model ID used for the prediction
data.outputs	array	Array of URLs to the generated content (empty when status is not `completed`)
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.has_nsfw_contents	array	Array of boolean values indicating NSFW detection for each output
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Result Query Parameters

Result Request Parameters

Parameter	Type	Required	Default	Description
id	string	Yes	-	Task ID

Result Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data	object	The prediction data object containing all details
data.id	string	Unique identifier for the prediction, the ID of the prediction to get
data.model	string	Model ID used for the prediction
data.outputs	array	Array of URLs to the generated content (empty when status is not `completed`)
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.has_nsfw_contents	array	Array of boolean values indicating NSFW detection for each output
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Kwaivgi Kling V2.1 I2v Pro Kwaivgi Kling V2.1 T2v Master