MODEL ID runware:210@1

live

Kandinsky 5.0 Lite

September 29, 2025

Kandinsky 5.0 Lite is a 2B parameter text to video model tuned for 5 and 10 second clips. It renders painterly motion with rich color and smooth transitions. It targets lower GPU memory, faster inference, and strong prompt adherence for creative production workflows.

API Options

Platform-level options for task execution and delivery.

taskType string required value: videoInference: Identifier for the type of task being performed

taskUUID string required UUID v4: UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

outputType string default: URL: Video output type.

Allowed values 1 value

outputFormat string default: MP4

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

`MP4`: Widely supported video container (H.264), recommended for general use.
`WEBM`: Optimized for web delivery.
`MOV`: QuickTime format, common in professional workflows (Apple ecosystem).

Allowed values 3 values

outputQuality integer min: 20 max: 99 default: 95: Compression quality of the output. Higher values preserve quality but increase file size.

webhookURL string URI

Specifies a webhook URL where JSON responses will be sent via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

Learn more 1 resource

Webhooks
PLATFORM

deliveryMethod string default: async

Determines how the API delivers task results.

Allowed values 1 value

: Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse. Required for long-running tasks like video generation.

Learn more 1 resource

Task Polling
PLATFORM

uploadEndpoint string URI

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

Common use cases:

Cloud storage: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
CDN integration: Upload to content delivery networks for immediate distribution.

// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg

The content data will be sent as the request body to the specified URL when generation is complete.

safety object

Content safety checking configuration for video generation.

Properties 2 properties

safety » checkContent checkContent boolean default: false: Enable or disable content safety checking. When enabled, defaults to fast mode.

safety » mode mode string default: none

Safety checking mode for video generation.

Allowed values 3 values

: Disables checking.
: Checks key frames.
: Checks all frames.

ttl integer min: 60: Time-to-live (TTL) in seconds for generated content. Only applies when outputType is URL.

includeCost boolean default: false: Include task cost in the response.

numberResults integer min: 1 max: 4 default: 1: Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

Generation Parameters

Core parameters for controlling the generated content.

model string required value: runware:210@1

Identifier of the model to use for generation.

Learn more 3 resources

positivePrompt string required min: 2

Text prompt describing elements to include in the generated output.

Learn more 2 resources

negativePrompt string

Prompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1).

Learn more 1 resource

Text To Image: Prompts Guiding The Generation
GUIDE

width integer required min: 512 max: 768 step: 16

Width of the generated media in pixels.

Excluded values 4 values

592656688752

Learn more 2 resources

height integer required min: 512 max: 768 step: 16

Height of the generated media in pixels.

Excluded values 4 values

592656688752

Learn more 2 resources

duration float required: Length of the generated video in seconds. The total number of frames produced is determined by duration multiplied by the model's frame rate (fps).

Allowed values 2 values

seed integer min: 0 max: 9223372036854776000

Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

Learn more 1 resource

Text To Image: Seed Controlling Randomness Deterministically
GUIDE

steps integer min: 1 max: 50 default: 20

Total number of denoising steps. Higher values generally produce more detailed results but take longer.

Learn more 1 resource

Text To Image: Steps Trading Quality For Speed
GUIDE

scheduler string

Scheduler to use for the diffusion process.

Allowed values 75 values

Learn more 2 resources

CFGScale float min: 1 max: 7 step: 0.01 default: 5

Guidance scale representing how closely the output will resemble the prompt. Higher values produce results more aligned with the prompt.

Learn more 1 resource

Text To Image: Cfg Scale Balancing Creativity And Control
GUIDE

taskType string required value: videoInference: Type of the task.

taskUUID string required UUID v4: UUID of the task.

videoUUID string required UUID v4: UUID of the output video.

videoURL string URI: URL of the output video.

videoBase64Data string: Base64-encoded video data.

videoDataURI string URI: Data URI of the output video.

seed integer: The seed used for generation. If none was provided, shows the randomly generated seed.

NSFWContent boolean: Flag indicating if NSFW content was detected.

cost float: Task cost in USD. Present when includeCost is set to true in the request.

Text to Video

Lantern Train Through Cypress Marsh

Request

{
  "taskType": "videoInference",
  "taskUUID": "c1a6704a-b82a-4f25-b645-a79a6b27aa7d",
  "model": "runware:210@1",
  "positivePrompt": "A storybook-inspired steam train with glowing amber lanterns glides slowly along a narrow track through a vast cypress marsh at blue hour. Tall trees rise from still water, their trunks mirrored in rippling reflections. Fireflies swirl in loose spirals above lily pads, reeds bend softly in the breeze, and pale mist curls between the roots. The camera makes a smooth side-tracking move, revealing warm carriage windows, drifting steam, and shimmering highlights across the water. Painterly textures, saturated teal and copper palette, dreamy cinematic atmosphere, graceful motion, highly cohesive composition.",
  "negativePrompt": "text, watermark, logo, low detail, blurry, jittery motion, flicker, distorted train, extra carriages, duplicate trees, noisy image, harsh cuts, oversaturated skin tones, modern city elements",
  "width": 768,
  "height": 512,
  "duration": 10,
  "seed": 28826,
  "steps": 28,
  "CFGScale": 5.5
}

Response

{
  "taskType": "videoInference",
  "taskUUID": "c1a6704a-b82a-4f25-b645-a79a6b27aa7d",
  "videoUUID": "37bf3171-61ab-4758-a3ae-6dd5c9b17e7f",
  "videoURL": "https://vm.runware.ai/video/os/a10d08/ws/5/vi/37bf3171-61ab-4758-a3ae-6dd5c9b17e7f.mp4",
  "seed": 28826,
  "cost": 0.2567
}

Text to Video

Glacial Cathedral Lantern Procession

Request

{
  "taskType": "videoInference",
  "taskUUID": "27dd563b-9b30-4aec-9139-d9745c3e3885",
  "model": "runware:210@1",
  "positivePrompt": "Inside a vast cathedral carved from blue glacier ice, a solemn procession of masked pilgrims carries amber lanterns along a crystalline aisle. The camera glides forward at a slow cinematic pace as hanging icicles glitter overhead, frosted arches refract warm light, and faint mist curls around the floor. In the distance, a colossal frozen rose window catches the lantern glow and scatters prismatic colors across the chamber. Painterly fantasy style, rich saturated blues and golds, elegant ceremonial costumes, gentle cloth motion, soft atmospheric haze, reflective surfaces, smooth transitions, highly cohesive composition, immersive depth.",
  "negativePrompt": "text, watermark, logo, low detail, jittery motion, flicker, duplicated figures, deformed hands, extra limbs, blurry faces, harsh cuts, flat lighting, oversaturated skin, noise, compression artifacts",
  "width": 768,
  "height": 512,
  "duration": 10,
  "seed": 55780,
  "steps": 30,
  "CFGScale": 5.5
}

Response

{
  "taskType": "videoInference",
  "taskUUID": "27dd563b-9b30-4aec-9139-d9745c3e3885",
  "videoUUID": "dd7e4ddc-41c7-40f1-a0b9-3fd25178a04a",
  "videoURL": "https://vm.runware.ai/video/os/a22d05/ws/5/vi/dd7e4ddc-41c7-40f1-a0b9-3fd25178a04a.mp4",
  "seed": 55780,
  "cost": 0.2624
}

Text to Video

Amber Funicular Through Redwoods

Request

{
  "taskType": "videoInference",
  "taskUUID": "98d2855b-0c15-4eea-a7bd-6b55d2aedb81",
  "model": "runware:210@1",
  "positivePrompt": "A vintage mountain funicular with glowing amber windows ascends a steep track through colossal redwood trees at blue hour, painterly cinematic style, drifting ground fog, mossy trunks, tiny sparks from the cable mechanism, passengers visible as silhouettes, the camera glides alongside then gently rises above the treetops to reveal a hidden hilltop tea pavilion with warm paper lamps, rich brushlike textures, deep greens and copper highlights, smooth motion, strong sense of depth, expressive color transitions, highly detailed environment",
  "negativePrompt": "text, watermark, logo, low detail, flicker, jitter, deformed vehicle, duplicated trees, broken perspective, harsh strobing, noisy frames",
  "width": 768,
  "height": 512,
  "duration": 10,
  "seed": 75011,
  "steps": 30,
  "CFGScale": 5.5
}

Response

{
  "taskType": "videoInference",
  "taskUUID": "98d2855b-0c15-4eea-a7bd-6b55d2aedb81",
  "videoUUID": "336ff185-a4fc-40c7-b439-aced92023a7c",
  "videoURL": "https://vm.runware.ai/video/os/a15d18/ws/5/vi/336ff185-a4fc-40c7-b439-aced92023a7c.mp4",
  "seed": 75011,
  "cost": 0.2733
}

Text to Video

Porcelain Garden Tea Rite

Request

{
  "taskType": "videoInference",
  "taskUUID": "dd510304-ad1d-40d8-be9c-899d3669549d",
  "model": "runware:210@1",
  "positivePrompt": "A serene imperial garden courtyard at first light, centered on an elaborate tea rite beside a koi pond shaped like a crescent. Silk banners drift gently between flowering plum trees, pale porcelain lanterns glow softly under carved eaves, and a low lacquer table holds steaming teaware with curling vapor. A dignified host in layered robes performs slow precise movements while bright koi circle beneath floating petals. The camera glides forward and slightly arcs to reveal intricate stone paths, miniature bridges, ripples across the water, and distant pagoda silhouettes softened by mist. Painterly animation, lush brush-texture rendering, elegant color harmony of jade, coral, ivory, and gold, smooth transitions, refined atmosphere, cinematic depth, highly detailed yet poetic.",
  "negativePrompt": "low detail, blurry, noisy, flicker, jitter, warped hands, extra limbs, duplicated objects, deformed faces, text, watermark, logo, harsh strobe lighting, modern clothing, vehicles, sci-fi elements",
  "width": 768,
  "height": 512,
  "duration": 10,
  "seed": 78796,
  "steps": 28,
  "CFGScale": 5.5
}

Response

{
  "taskType": "videoInference",
  "taskUUID": "dd510304-ad1d-40d8-be9c-899d3669549d",
  "videoUUID": "79ae30fc-461c-44b0-a7fa-4d18fd43606f",
  "videoURL": "https://vm.runware.ai/video/os/a03d21/ws/5/vi/79ae30fc-461c-44b0-a7fa-4d18fd43606f.mp4",
  "seed": 78796,
  "cost": 0.2471
}