{ "openapi": "3.1.0", "info": { "title": "Runware API - alibaba-wan2-2-a14b-turbo", "version": "1.0.0", "description": "Wan2.2 A14B Turbo accelerates Wan2.2 with fused Lightning LoRA for ultra fast diffusion. It cuts inference to 8 steps while preserving cinematic structure and detail. Ideal for rapid 480p to 720p video prototyping and iteration in production workflows." }, "servers": [ { "url": "https://api.runware.ai/v1", "description": "Runware REST API" } ], "components": { "securitySchemes": { "apiKeyAuth": { "type": "http", "scheme": "bearer", "description": "Runware API Key (e.g., Bearer )" } }, "schemas": { "AuthenticationTask": { "title": "Authentication", "description": "Authenticates a connection using an API key. Can be sent as the first element of the request array as an alternative to using the Authorization header.", "type": "object", "x-response-schema": "https://schemas.runware.ai/responses/utilities/authentication.json", "properties": { "taskType": { "const": "authentication", "title": "Task Type", "description": "The type of task to perform." }, "apiKey": { "title": "API Key", "description": "Your Runware API key.", "type": "string" }, "connectionSessionUUID": { "title": "Connection Session UUID", "description": "Optional session UUID to resume a previous connection and receive any buffered results.", "type": "string", "format": "uuid" } }, "required": [ "taskType", "apiKey" ], "additionalProperties": false }, "RequestBody": { "type": "array", "items": { "type": "object", "properties": { "model": { "title": "Model", "description": "Identifier of the model to use for generation.", "type": "string", "const": "runware:200@8" }, "inputs": { "title": "Inputs", "description": "The unified payload wrapper for complex media assets dictating image, video or audio inference constraints.", "type": "object", "properties": { "frameImages": { "title": "Frame Images", "description": "An array of objects that define key frames to guide video generation. Each object specifies an input image and optionally its position within the video timeline.\n\nThe `frameImages` parameter allows you to constrain specific frames within the video sequence, ensuring that particular visual content appears at designated points. This is different from `referenceImages`, which provide overall visual guidance without constraining specific timeline positions.\n\nWhen the `frame` parameter is omitted from objects, automatic distribution rules apply:\n\n- **1 image**: Used as the first frame.\n- **2 images**: First and last frames.\n- **3+ images**: First and last frames, with intermediate images evenly spaced between.\n\n**Examples**:\n\n**Single frame (automatic positioning):** When only one image is provided, it automatically becomes the first frame of the video.\n\n```json\n\"frameImages\": [\n {\n \"image\": \"aac49721-1964-481a-ae78-8a4e29b91402\"\n }\n]\n```\n\n**First and last frames:** With two images, they automatically become the first and last frames of the video sequence.\n\n```json\n\"frameImages\": [\n {\n \"image\": \"aac49721-1964-481a-ae78-8a4e29b91402\",\n \"frame\": \"first\"\n },\n {\n \"image\": \"3ad204c3-a9de-4963-8a1a-c3911e3afafe\",\n \"frame\": \"last\"\n }\n]\n```\n\n**Multiple frames:** With three or more images, the first and last are anchored while intermediate frames are evenly distributed across the timeline.\n\n```json\n\"frameImages\": [\n {\n \"image\": \"aac49721-1964-481a-ae78-8a4e29b91402\",\n \"frame\": \"first\"\n },\n {\n \"image\": \"c00abf5f-6cdb-4642-a01d-1bfff7bc3cf7\"\n },\n {\n \"image\": \"3ad204c3-a9de-4963-8a1a-c3911e3afafe\",\n \"frame\": \"last\"\n }\n]\n```\n\n[Read full documentation](https://runware.ai/docs/models/alibaba-wan2-2-a14b-turbo#frameImages)", "type": "array", "minItems": 1, "items": { "type": "object", "properties": { "image": { "title": "Image", "description": "Image input (UUID, URL, Data URI, or Base64).", "type": "string", "anyOf": [ { "format": "uuid" }, { "format": "uri" }, { "pattern": "^data:image\\/[a-zA-Z]+;base64,[a-zA-Z0-9+/=]+$" }, { "pattern": "^[a-zA-Z0-9+/=]+$" } ] }, "frame": { "title": "Frame", "description": "Target frame position for the image. Supports first and last frame.", "oneOf": [ { "const": "first", "description": "First frame of the video." }, { "const": "last", "description": "Last frame of the video." }, { "const": 0, "description": "Frame index 0 (first frame)." }, { "const": -1, "description": "Frame index -1 (last frame)." } ] } }, "required": [ "image" ], "additionalProperties": false }, "maxItems": 2 } }, "additionalProperties": false }, "positivePrompt": { "title": "Positive Prompt", "description": "Text prompt describing elements to include in the generated output.", "type": "string", "minLength": 2, "maxLength": 3000 }, "negativePrompt": { "title": "Negative Prompt", "description": "Prompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1).", "type": "string", "minLength": 2, "maxLength": 3000 }, "width": { "title": "Width", "description": "Width of the generated media in pixels.", "type": "integer" }, "height": { "title": "Height", "description": "Height of the generated media in pixels.", "type": "integer" }, "resolution": { "title": "Resolution", "description": "Resolution preset for the output. When used with input media, automatically matches the aspect ratio from the input.", "type": "string", "enum": [ "480p", "580p", "720p" ] }, "duration": { "definitions": { "video": { "$id": "https://schemas.runware.ai/parameters/generation/duration.json?def=video", "title": "Duration", "description": "Length of the generated video in seconds. The total number of frames produced is determined by duration multiplied by the model's frame rate (fps).", "type": "number" }, "audio": { "$id": "https://schemas.runware.ai/parameters/generation/duration.json?def=audio", "title": "Duration", "description": "Length of the generated audio track in seconds.", "type": "number" } }, "type": "integer", "minimum": 1, "maximum": 15 }, "fps": { "title": "FPS", "description": "Frames per second for video generation. Higher values create smoother motion but require more processing time.", "type": "integer", "minimum": 16, "maximum": 60 }, "seed": { "title": "Seed", "description": "Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.", "type": "integer", "minimum": 0, "maximum": 9223372036854776000 }, "steps": { "title": "Steps", "description": "Total number of denoising steps. Higher values generally produce more detailed results but take longer.", "type": "integer", "minimum": 4, "default": 20, "maximum": 50 }, "scheduler": { "title": "Scheduler", "description": "Scheduler to use for the diffusion process.", "type": "string", "enum": [ "DDIM", "DDIMScheduler", "DDPMScheduler", "DEISMultistepScheduler", "Default", "DPM++", "DPM++ 2M", "DPM++ 2M Beta", "DPM++ 2M Exponential", "DPM++ 2M Karras", "DPM++ 2M SDE", "DPM++ 2M SDE Beta", "DPM++ 2M SDE Exponential", "DPM++ 2M SDE Karras", "DPM++ 2M SDE Uniform", "DPM++ 2M Uniform", "DPM++ 3M", "DPM++ 3M Beta", "DPM++ 3M Exponential", "DPM++ 3M Karras", "DPM++ 3M SDE Uniform", "DPM++ 3M Uniform", "DPM++ Beta", "DPM++ Exponential", "DPM++ Karras", "DPM++ SDE", "DPM++ SDE Beta", "DPM++ SDE Exponential", "DPM++ SDE Karras", "DPM++ Uniform", "DPM++ Uniform Beta", "DPM++ Uniform Exponential", "DPM++ Uniform Karras", "DPMSolverMultistepInverse", "DPMSolverMultistepScheduler", "DPMSolverSinglestepScheduler", "EDMDPMSolverMultistepScheduler", "EDMEulerScheduler", "Euler", "Euler a", "Euler Beta", "Euler DiscreteScheduler", "Euler Exponential", "Euler Karras", "EulerAncestralDiscreteScheduler", "FlowMatchEulerDiscreteScheduler", "Heun", "HeunDiscreteScheduler", "Heun Karras", "IPNDMScheduler", "IPNDM Uniform", "IPNDM Uniform Beta", "IPNDM Uniform Exponential", "IPNDM Uniform Karras", "KDPM2AncestralDiscreteScheduler", "KDPM2DiscreteScheduler", "LCM", "LCMScheduler", "LMS", "LMSDiscreteScheduler", "LMS Karras", "PNDMScheduler", "TCDScheduler", "UniPC", "UniPC 2M", "UniPC 2M Karras", "UniPC 2M Uniform", "UniPC 3M", "UniPC 3M Karras", "UniPC 3M Uniform", "UniPC Karras", "UniPC Uniform", "UniPC Uniform Beta", "UniPC Uniform Exponential", "UniPC Uniform Karras" ] }, "CFGScale": { "title": "CFG Scale", "description": "Guidance scale representing how closely the output will resemble the prompt. Higher values produce results more aligned with the prompt.", "type": "number", "multipleOf": 0.01, "minimum": 0.1, "maximum": 30 }, "acceleration": { "title": "Acceleration Option", "description": "Optimization level.", "type": "string", "enum": [ "none", "low", "medium", "high" ], "default": "none" }, "acceleratorOptions": { "title": "Accelerator Options", "description": "Advanced caching mechanisms to speed up generation.", "type": "object", "properties": { "cacheEndStep": { "title": "Cache End Step", "description": "Absolute step number to end caching. Must be greater than `cacheStartStep` and less than or equal to `steps`.", "type": "integer", "minimum": 1 }, "cacheEndStepPercentage": { "title": "Cache End Step Percentage", "description": "Percentage of steps to end caching. Alternative to `cacheEndStep`. Must be greater than `cacheStartStepPercentage`.", "type": "integer", "minimum": 1, "maximum": 100 }, "cacheMaxConsecutiveSteps": { "title": "Cache Max Consecutive Steps", "description": "Limits the maximum number of consecutive steps that can use cached computations before forcing a fresh computation.", "type": "integer", "minimum": 1, "maximum": 5, "default": 3 }, "cacheStartStep": { "title": "Cache Start Step", "description": "Absolute step number to start caching. Must be less than `cacheEndStep`.", "type": "integer", "minimum": 0 }, "cacheStartStepPercentage": { "title": "Cache Start Step Percentage", "description": "Percentage of steps to start caching. Alternative to `cacheStartStep`. Must be less than `cacheEndStepPercentage`.", "type": "integer", "minimum": 0, "maximum": 99 }, "fbCache": { "title": "FB Cache", "description": "First Block Cache (FBCache) acceleration. Reuses feature block computations across steps.", "type": "boolean", "default": false }, "fbCacheThreshold": { "title": "FB Cache Threshold", "description": "Controls the sensitivity threshold for determining when to reuse cached computations. Lower values reuse more aggressively.", "type": "number", "multipleOf": 0.01, "minimum": 0, "maximum": 1, "default": 0.25 }, "teaCache": { "title": "TeaCache", "description": "TeaCache acceleration for transformer-based models. Estimates step differences to skip redundant computations.", "type": "boolean", "default": false }, "teaCacheDistance": { "title": "TeaCache Distance", "description": "Controls the aggressiveness of the TeaCache feature. Lower values prioritize quality, higher values prioritize speed.", "type": "number", "multipleOf": 0.01, "minimum": 0, "maximum": 1, "default": 0.5 }, "dbCache": { "title": "DB Cache", "description": "DB Cache (CacheDiT) acceleration. Caches and reuses intermediate transformer block outputs to skip redundant computations.", "type": "boolean", "default": false }, "dbCacheThreshold": { "title": "DB Cache Threshold", "description": "Controls the sensitivity threshold for DB Cache. Lower values reuse cached blocks more aggressively, higher values prioritize quality.", "type": "number", "multipleOf": 0.01, "minimum": 0, "maximum": 1, "default": 0.25 }, "dbCacheSkipInterval": { "title": "DB Cache Skip Interval", "description": "Controls how many steps to skip between cache refreshes. Higher values skip more steps for faster generation at the cost of quality.", "type": "integer", "minimum": 1, "default": 5 } }, "allOf": [ { "not": { "required": [ "cacheStartStep", "cacheStartStepPercentage" ] } }, { "not": { "required": [ "cacheEndStep", "cacheEndStepPercentage" ] } } ], "additionalProperties": false }, "lora": { "title": "LoRA", "description": "---\n\nresources:\n\n- [https://runware.ai/docs/guides/text-to-image#loras-style-and-subject-adapters](https://runware.ai/docs/guides/text-to-image#loras-style-and-subject-adapters)\n\n---\n\nWith LoRA (Low-Rank Adaptation), you can adapt a model to specific styles or features by emphasizing particular aspects of the data. This technique enhances the quality and relevance of generated content and can be especially useful when the output needs to adhere to a specific artistic style or follow particular guidelines.\n\nMultiple LoRA models can be used simultaneously to achieve different adaptation goals.\n\n**Examples**:\n\n```json\n\"lora\": [\n {\n \"model\": \"\",\n \"weight\": 0.8\n }\n]\n```\n\n[Read full documentation](https://runware.ai/docs/models/alibaba-wan2-2-a14b-turbo#lora)", "type": "array", "minItems": 1, "items": { "type": "object", "properties": { "model": { "title": "LoRA Model", "description": "LoRA model identifier.", "type": "string", "pattern": "^[a-zA-Z0-9._-]+(:[a-zA-Z0-9._/@-]+)?$" }, "weight": { "title": "LoRA Weight", "description": "Strength of the LoRA influence. A value of 0 means no influence. Higher values increase the influence, and negative values can be used to steer away from the LoRA's style.", "type": "number", "multipleOf": 0.01, "minimum": -4, "maximum": 4, "default": 1 }, "transformer": { "title": "LoRA Transformer", "description": "Transformer stages to apply LoRA. Some video models use separate high-noise and low-noise processing stages, and LoRAs can be selectively applied to optimize their effectiveness.", "type": "string", "oneOf": [ { "const": "high", "title": "High", "description": "Apply LoRA only to the high-noise processing stage (coarse structure and early generation steps)." }, { "const": "low", "title": "Low", "description": "Apply LoRA only to the low-noise processing stage (fine details and later generation steps)." }, { "const": "both", "title": "Both", "description": "Apply LoRA to both stages for full coverage." } ], "default": "both" } }, "required": [ "model" ], "additionalProperties": false } }, "taskType": { "title": "Task Type", "description": "Identifier for the type of task being performed", "type": "string", "const": "videoInference" }, "taskUUID": { "title": "Task UUID", "description": "UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.", "type": "string", "format": "uuid" }, "webhookURL": { "title": "Webhook URL", "description": "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.", "type": "string", "format": "uri" }, "includeCost": { "title": "Include Cost", "description": "Include task cost in the response.", "type": "boolean", "default": false }, "numberResults": { "title": "Number of Results", "description": "Number of results to generate. Each result uses a different seed, producing variations of the same parameters.", "type": "integer", "minimum": 1, "maximum": 20, "default": 1 }, "uploadEndpoint": { "title": "Upload Endpoint", "description": "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.\n\n**Common use cases:**\n\n- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.\n- **CDN integration**: Upload to content delivery networks for immediate distribution.\n\n```text\n// S3 presigned URL for secure upload\nhttps://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600\n\n// Google Cloud Storage presigned URL\nhttps://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789\n\n// Custom storage endpoint\nhttps://storage.example.com/uploads/generated-image.jpg\n```\n\nThe content data will be sent as the request body to the specified URL when generation is complete.\n\n[Read full documentation](https://runware.ai/docs/models/alibaba-wan2-2-a14b-turbo#uploadEndpoint)", "type": "string", "format": "uri" }, "ttl": { "title": "TTL", "description": "Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.", "type": "integer", "minimum": 60 }, "outputType": { "title": "Output Type", "description": "Video output type.", "type": "string", "enum": [ "URL" ], "default": "URL" }, "outputFormat": { "title": "Output Format", "description": "Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.\n\n- \\`JPG\\`: Best for photorealistic images with smaller file sizes (no transparency).\n- \\`PNG\\`: Lossless compression, supports high quality and transparency (alpha channel).\n- \\`WEBP\\`: Modern format providing superior compression and transparency support.\n- \\`MP4\\`: Widely supported video container (H.264), recommended for general use.\n- \\`WEBM\\`: Optimized for web delivery.\n- \\`MOV\\`: QuickTime format, common in professional workflows (Apple ecosystem).\n- \\`GIF\\`: Animated image format (no audio), suitable for short loops or previews.\n- \\`MP3\\`: Compressed audio, smaller file size.\n- \\`WAV\\`: Uncompressed, high-quality audio.\n- \\`FLAC\\`: Lossless compression.\n- \\`SVG\\`: Scalable Vector Graphics.\n- \\`TIFF\\`: High-quality output supporting layers.\n\n> [!NOTE]\n> \\*\\*Transparency\\*\\*: If you are using features like background removal or LayerDiffuse that require transparency, you must select a format that supports an alpha channel (e.g., \\`PNG\\`, \\`WEBP\\`, \\`TIFF\\`). \\`JPG\\` does not support transparency.\n\n[Read full documentation](https://runware.ai/docs/models/alibaba-wan2-2-a14b-turbo#outputFormat)", "type": "string", "enum": [ "MP4", "WEBM", "MOV" ], "default": "MP4" }, "outputQuality": { "title": "Output Quality", "description": "Compression quality of the output. Higher values preserve quality but increase file size.", "type": "integer", "minimum": 20, "maximum": 99, "default": 95 }, "deliveryMethod": { "title": "Delivery Method", "description": "Determines how the API delivers task results.", "type": "string", "oneOf": [ { "const": "async", "description": "Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse. Required for long-running tasks like video generation." } ], "default": "async" }, "safety": { "type": "object", "title": "Safety Settings", "description": "Content safety checking configuration for video generation.", "properties": { "checkContent": { "title": "Check Content", "description": "Enable or disable content safety checking. When enabled, defaults to `fast` mode.", "type": "boolean", "default": false }, "mode": { "description": "Safety checking mode for video generation.", "type": "string", "oneOf": [ { "const": "none", "title": "None", "description": "Disables checking." }, { "const": "fast", "title": "Fast", "description": "Checks key frames." }, { "const": "full", "title": "Full", "description": "Checks all frames." } ], "default": "none" } }, "additionalProperties": false } }, "required": [ "positivePrompt", "taskType", "taskUUID", "model" ], "allOf": [ { "dependentRequired": { "width": [ "height" ], "height": [ "width" ] } }, { "oneOf": [ { "title": "480p (16:9)", "properties": { "width": { "const": 848 }, "height": { "const": 480 } } }, { "title": "480p (1:1)", "properties": { "width": { "const": 640 }, "height": { "const": 640 } } }, { "title": "480p (9:16)", "properties": { "width": { "const": 480 }, "height": { "const": 848 } } }, { "title": "480p (4:3)", "properties": { "width": { "const": 736 }, "height": { "const": 560 } } }, { "title": "480p (3:4)", "properties": { "width": { "const": 560 }, "height": { "const": 736 } } }, { "title": "580p (16:9)", "properties": { "width": { "const": 1024 }, "height": { "const": 576 } } }, { "title": "580p (1:1)", "properties": { "width": { "const": 768 }, "height": { "const": 768 } } }, { "title": "580p (9:16)", "properties": { "width": { "const": 576 }, "height": { "const": 1024 } } }, { "title": "580p (4:3)", "properties": { "width": { "const": 896 }, "height": { "const": 672 } } }, { "title": "580p (3:4)", "properties": { "width": { "const": 672 }, "height": { "const": 896 } } }, { "title": "720p (16:9)", "properties": { "width": { "const": 1280 }, "height": { "const": 720 } } }, { "title": "720p (1:1)", "properties": { "width": { "const": 960 }, "height": { "const": 960 } } }, { "title": "720p (9:16)", "properties": { "width": { "const": 720 }, "height": { "const": 1280 } } }, { "title": "720p (4:3)", "properties": { "width": { "const": 1104 }, "height": { "const": 832 } } }, { "title": "720p (3:4)", "properties": { "width": { "const": 832 }, "height": { "const": 1104 } } } ] }, { "if": { "not": { "properties": { "inputs": { "properties": { "frameImages": { "minItems": 1 } }, "required": [ "frameImages" ] } }, "required": [ "inputs" ] } }, "then": { "anyOf": [ { "required": [ "width", "height" ] }, { "required": [ "resolution" ] } ] } }, { "not": { "allOf": [ { "required": [ "resolution" ] }, { "anyOf": [ { "required": [ "width" ] }, { "required": [ "height" ] } ] } ] } }, { "not": { "allOf": [ { "properties": { "acceleratorOptions": { "required": [ "fbCache" ] } }, "required": [ "acceleratorOptions" ] }, { "properties": { "acceleratorOptions": { "required": [ "teaCache" ] } }, "required": [ "acceleratorOptions" ] } ] } } ], "additionalProperties": false }, "description": "You must always POST an array of task objects." }, "ResponseBody": { "type": "object", "properties": { "data": { "type": "array", "items": { "type": "object", "description": "Unknown response structure" } } } }, "ErrorResponse": { "title": "Error Response", "description": "Standard error response returned by the Runware API.", "type": "object", "properties": { "errors": { "type": "array", "items": { "type": "object", "required": [ "code", "message" ], "additionalProperties": true, "properties": { "code": { "type": "string", "description": "A short identifier for the error (e.g., invalidApiKey, timeoutProvider)." }, "message": { "type": "string", "description": "A human-readable explanation of what went wrong." }, "parameter": { "type": "string", "description": "The request parameter related to the error, if applicable." }, "taskType": { "type": "string", "description": "The task type of the request that failed." }, "taskUUID": { "type": "string", "description": "The unique identifier of the failed request." }, "documentation": { "type": "string", "description": "A link to relevant documentation." } } } } }, "required": [ "errors" ], "additionalProperties": false } } }, "paths": { "/": { "post": { "summary": "Run alibaba-wan2-2-a14b-turbo", "description": "Wan2.2 A14B Turbo accelerates Wan2.2 with fused Lightning LoRA for ultra fast diffusion. It cuts inference to 8 steps while preserving cinematic structure and detail. Ideal for rapid 480p to 720p video prototyping and iteration in production workflows.", "operationId": "run_alibaba_wan2_2_a14b_turbo", "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/RequestBody" } } } }, "responses": { "200": { "description": "Successful response", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ResponseBody" } } } }, "400": { "description": "Bad Request — Missing or invalid parameters.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "401": { "description": "Unauthorized — No valid API key provided.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "402": { "description": "Payment Required — Insufficient account balance.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "403": { "description": "Forbidden — The API key lacks permissions for this request.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "429": { "description": "Too Many Requests — Rate limit exceeded.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "500": { "description": "Server Error — Something went wrong on Runware's end.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "503": { "description": "Service Unavailable — Temporarily unavailable (maintenance or capacity).", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } } } } } }, "security": [ { "apiKeyAuth": [] } ] }