MODEL ID runware:190@1

live

Ovi

September 30, 2025

Ovi is a unified audio video diffusion model that treats sound and visuals as one generative process. It uses twin DiT backbones with blockwise cross modal fusion to create synchronized speech, effects, and motion from text prompts or text plus image inputs in a single pass.

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.

acceleratorOptions object

Advanced caching mechanisms to speed up generation.

Properties 7 properties

acceleratorOptions » cacheEndStep cacheEndStep integer min: 1: Absolute step number to end caching. Must be greater than cacheStartStep and less than or equal to steps.

acceleratorOptions » cacheEndStepPercentage cacheEndStepPercentage integer min: 1 max: 100: Percentage of steps to end caching. Alternative to cacheEndStep. Must be greater than cacheStartStepPercentage.

acceleratorOptions » cacheMaxConsecutiveSteps cacheMaxConsecutiveSteps integer min: 1 max: 5 default: 3: Limits the maximum number of consecutive steps that can use cached computations before forcing a fresh computation.

acceleratorOptions » cacheStartStep cacheStartStep integer min: 0: Absolute step number to start caching. Must be less than cacheEndStep.

acceleratorOptions » cacheStartStepPercentage cacheStartStepPercentage integer min: 0 max: 99: Percentage of steps to start caching. Alternative to cacheStartStep. Must be less than cacheEndStepPercentage.

acceleratorOptions » teaCache teaCache boolean default: false: TeaCache acceleration for transformer-based models. Estimates step differences to skip redundant computations.

acceleratorOptions » teaCacheDistance teaCacheDistance float min: 0 max: 1 step: 0.01 default: 0.5: Controls the aggressiveness of the TeaCache feature. Lower values prioritize quality, higher values prioritize speed.

Inputs

Input resources for the task (images, audio, etc). These must be nested inside the inputs object.

inputs » image image string required: Image input (UUID, URL, Data URI, or Base64).

Generation Parameters

Core parameters for controlling the generated content.

model string required value: runware:190@1

Identifier of the model to use for generation.

Learn more 3 resources

positivePrompt string required

Text prompt describing elements to include in the generated output.

Learn more 2 resources

fps integer max: 120 default: 24: Frames per second for video generation. Higher values create smoother motion but require more processing time.

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: 100 default: 30

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

Features

Standalone addons and post-processing features.

advancedFeatures » audioCFGScale audioCFGScale float min: 0 max: 10 default: 4: Classifier-free guidance scale for the audio diffusion process. Higher values increase adherence to the text prompt.

advancedFeatures » audioNegativePrompt audioNegativePrompt string: Text describing elements to avoid in the generated audio.

advancedFeatures » slgLayer slgLayer integer min: 0 max: 30: Skip-layer guidance layer index. Set to null to disable.

advancedFeatures » videoCFGScale videoCFGScale float min: 0 max: 10 default: 5: Classifier-free guidance scale for the video diffusion process. Higher values increase adherence to the text prompt.

advancedFeatures » videoNegativePrompt videoNegativePrompt string: Text describing elements to avoid in the generated video.

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.

Image to Video

Rain-Soaked Arcade Concourse

Request

{
  "taskType": "videoInference",
  "taskUUID": "fd9a5ac6-7acc-44ef-a961-cf55b99e41cd",
  "model": "runware:190@1",
  "positivePrompt": "Animate this rainy retro-futurist arcade concourse into a cohesive audiovisual sequence. The camera drifts forward at walking pace through the passageway as puddles ripple under falling droplets from ceiling leaks. Game cabinet screens pulse and flicker in staggered rhythms, vending machines hum softly, and reflected colors slide across the wet floor. A tram glides past in the background beyond the arches, sending a low metallic rumble through the space. People in translucent raincoats cross frame naturally, some pausing at machines, others hurrying through, with believable footfalls, fabric rustle, distant chatter, and reverberant ambience. Occasional thunder rolls outside and the electrical buzz subtly swells as lights blink overhead. Preserve the composition of the source image while adding cinematic motion, synchronized environmental sound, layered depth, and realistic timing.",
  "fps": 24,
  "seed": 71241,
  "steps": 30,
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/839ea199-a462-46b8-90ce-c703cac214f3.jpg"
  }
}

Response

{
  "taskType": "videoInference",
  "taskUUID": "fd9a5ac6-7acc-44ef-a961-cf55b99e41cd",
  "videoUUID": "4585f688-3f56-4cdf-9750-de1343c9d355",
  "videoURL": "https://vm.runware.ai/video/os/a10dlim3/ws/5/vi/4585f688-3f56-4cdf-9750-de1343c9d355.mp4",
  "seed": 71241,
  "cost": 0.1171
}

Image to Video

Stormy Lighthouse Rescue Approach

Request

{
  "taskType": "videoInference",
  "taskUUID": "6537bd8a-b38e-4579-9b6f-7f48cd2f4f38",
  "model": "runware:190@1",
  "positivePrompt": "Animate this storm-battered lighthouse scene into a high-tension cinematic rescue sequence. The helicopter advances through heavy rain and crosswinds, rotor blades slicing mist into spiraling sheets. The lighthouse beacon sweeps across the sea and briefly catches the aircraft fuselage. Waves hammer the rocks in irregular bursts, white spray rising with each impact. Lightning flashes intermittently, revealing texture in the clouds and ocean surface. Camera feel: slow forward drift with subtle handheld turbulence, as if filmed from another aircraft nearby. Motion should feel physically grounded and coherent: rain driven sideways by wind, foam dragged back into the surf, helicopter navigation lights pulsing through the storm, searchlight glancing across wet stone. Audio should emerge naturally from the scene with synchronized thunder cracks, rotor thrum, wind gusts, rain striking metal, distant warning siren from the lighthouse, and booming surf. Moody, realistic, suspenseful, immersive.",
  "fps": 24,
  "seed": 79445,
  "steps": 40,
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/597fde48-a2bd-4a5b-a57d-2e8673b348e1.jpg"
  }
}

Response

{
  "taskType": "videoInference",
  "taskUUID": "6537bd8a-b38e-4579-9b6f-7f48cd2f4f38",
  "videoUUID": "885007e4-58d3-42e8-9bca-5fa150e75eb7",
  "videoURL": "https://vm.runware.ai/video/os/a05d22/ws/5/vi/885007e4-58d3-42e8-9bca-5fa150e75eb7.mp4",
  "seed": 79445,
  "cost": 0.1472
}

Image to Video

Glacial Freight Terminal Dawn

Request

{
  "taskType": "videoInference",
  "taskUUID": "88fd8e24-b83e-45fd-b606-63f6d3cf3093",
  "model": "runware:190@1",
  "positivePrompt": "A cinematic aerial drift through a remote polar freight terminal at dawn, starting from a wide establishing view and gliding toward docked cargo airships as ground crews move between steel loading gantries. Fine snow streams across the frozen tarmac, turbine fans spool up with visible exhaust haze, suspended cables sway lightly in the wind, warning beacons blink in rhythmic intervals, and distant cargo containers shift on automated sleds. Emphasize realistic environmental motion, crisp cold atmosphere, volumetric breath from workers, subtle camera parallax, and synchronized industrial soundscape with gusting wind, engine rumble, metallic clanks, radio chatter, hydraulic whines, and echoing announcements. Naturalistic, high-detail, grounded cinematic realism.",
  "fps": 24,
  "seed": 14447,
  "steps": 40,
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/da99c2f7-1bb5-466a-a313-bd44026f790d.jpg"
  }
}

Response

{
  "taskType": "videoInference",
  "taskUUID": "88fd8e24-b83e-45fd-b606-63f6d3cf3093",
  "videoUUID": "4344d183-7c03-4256-9ab7-d5af1cc20627",
  "videoURL": "https://vm.runware.ai/video/os/a05d22/ws/5/vi/4344d183-7c03-4256-9ab7-d5af1cc20627.mp4",
  "seed": 14447,
  "cost": 0.1459
}

Image to Video

Windblown Grassland Radio Relay

Request

{
  "taskType": "videoInference",
  "taskUUID": "c4bdc7a1-ae63-476b-818c-d89d64111c00",
  "model": "runware:190@1",
  "positivePrompt": "Animate this still image into a grounded cinematic scene: strong wind ripples through tall grass in waves, guy-wires tremble subtly, loose tarp edge flickers, the service truck suspension shifts slightly in gusts, cloud shadows drift across the field, a flock of small birds lifts from the grass in the distance, the antenna beacon blinks faintly, synchronized natural audio with rushing wind, soft metal creaks, distant turbine-like electrical hum, intermittent radio static and clipped voice fragments from the relay shed, realistic motion, coherent environmental sound design, atmospheric documentary style",
  "fps": 24,
  "seed": 99804,
  "steps": 40,
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/42361c12-04bc-489d-8036-61b72bfa935a.jpg"
  }
}

Response

{
  "taskType": "videoInference",
  "taskUUID": "c4bdc7a1-ae63-476b-818c-d89d64111c00",
  "videoUUID": "e1373a2c-ce29-425a-8413-64149a954294",
  "videoURL": "https://vm.runware.ai/video/os/a03d21/ws/5/vi/e1373a2c-ce29-425a-8413-64149a954294.mp4",
  "seed": 99804,
  "cost": 0.1466
}