> ## Documentation Index > Fetch the complete documentation index at: https://docs.modellix.ai/llms.txt > Use this file to discover all available pages before exploring further. # SkyReels Image-to-Video > **[Core Function]** SkyReels Image-to-Video animates one or more keyframe images into a video guided by a text prompt. **[Strengths]** Supports a start frame, an end frame, and tagged mid-frames for keyframe control; optional audio, 480p/720p/1080p output, and fast/std modes. **[Best For]** Bringing a photo to life, first-last-frame transitions, and keyframe-driven storyboards. **[Limitations]** Do NOT use this for pure text-to-video (use skyreels-t2v) or for editing an existing video (use the Omni / video-to-video models). It requires at least one of first_frame_image, end_frame_image, or mid_frame_images; output is capped at 1080p and 15s, and fast mode supports only sound=false. **[Routing]** Provide first_frame_image to animate from a start image, add end_frame_image for a transition, or supply mid_frame_images (each tag must appear in the prompt as @tag) for keyframe guidance. ## OpenAPI ````yaml /model-api/skywork/skyreels-i2v.json post /skywork/skyreels-i2v openapi: 3.1.0 info: description: >- The image-to-video models API from SkyReels (Skywork). Includes keyframe image-to-video, multi-subject reference-to-video, and audio-driven talking-avatar generation. Tasks are asynchronous: submit, then poll the task endpoint for the result. version: 1.0.0 contact: name: Modellix Support email: support@modellix.ai title: SkyReels Image-to-Video Models API servers: - url: https://api.modellix.ai/api/v1 description: The image-to-video models API from SkyReels (Skywork). security: - bearerAuth: [] paths: /skywork/skyreels-i2v: post: summary: SkyReels Image-to-Video description: >- **[Core Function]** SkyReels Image-to-Video animates one or more keyframe images into a video guided by a text prompt. **[Strengths]** Supports a start frame, an end frame, and tagged mid-frames for keyframe control; optional audio, 480p/720p/1080p output, and fast/std modes. **[Best For]** Bringing a photo to life, first-last-frame transitions, and keyframe-driven storyboards. **[Limitations]** Do NOT use this for pure text-to-video (use skyreels-t2v) or for editing an existing video (use the Omni / video-to-video models). It requires at least one of first_frame_image, end_frame_image, or mid_frame_images; output is capped at 1080p and 15s, and fast mode supports only sound=false. **[Routing]** Provide first_frame_image to animate from a start image, add end_frame_image for a transition, or supply mid_frame_images (each tag must appear in the prompt as @tag) for keyframe guidance. operationId: skyreelsI2VAsync requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/SkyreelsI2VRequest' examples: firstFrame: summary: Animate from a start image value: prompt: The man slowly turns toward the camera and smiles first_frame_image: https://example.com/portrait.png duration: 5 resolution: 1080p mode: std keyframes: summary: Keyframe guidance with mid-frame value: prompt: The dragon in @image1 takes off and flies over the village first_frame_image: https://example.com/start.png end_frame_image: https://example.com/end.png mid_frame_images: - tag: '@image1' image_url: https://example.com/mid.png time_stamp: 2 duration: 5 responses: '200': description: Task submitted successfully content: application/json: schema: $ref: '#/components/schemas/AsyncTaskResponse' example: code: 0 message: success data: status: pending task_id: task-skyreels-i2v-001 model_id: skyreels/skyreels-i2v get_result: method: GET url: https://api.modellix.ai/api/v1/tasks/task-skyreels-i2v-001 '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '429': $ref: '#/components/responses/TooManyRequests' '500': $ref: '#/components/responses/InternalServerError' components: schemas: SkyreelsI2VRequest: type: object required: - prompt description: >- SkyReels image-to-video request. prompt is required; at least one of first_frame_image, end_frame_image, or mid_frame_images must be provided. Other fields fall back to provider defaults. properties: prompt: type: string minLength: 1 description: Text description of the video to generate (max 1280 tokens). example: The man slowly turns toward the camera and smiles first_frame_image: type: string minLength: 1 description: Start frame image URL (jpg/jpeg/png/gif/bmp). example: https://example.com/portrait.png end_frame_image: type: string minLength: 1 description: End frame image URL (jpg/jpeg/png/gif/bmp). example: https://example.com/end.png mid_frame_images: type: array description: >- Optional mid-frame keyframes. Each tag must be referenced in the prompt via @tag. items: $ref: '#/components/schemas/MidFrameImage' duration: type: integer minimum: 3 maximum: 15 default: 5 description: Video duration in seconds. example: 5 resolution: type: string enum: - 480p - 720p - 1080p default: 1080p description: Output video resolution. example: 1080p mode: type: string enum: - fast - std default: std description: >- Quality/performance mode. fast is quicker (sound must be false); std balances speed and quality. example: std sound: type: boolean default: false description: Whether to generate audio. Not supported when mode=fast. example: false prompt_optimizer: type: boolean default: true description: Enable automatic prompt expansion/optimization. example: true AsyncTaskResponse: type: object required: - code - message - data properties: code: type: integer description: Response code, 0 indicates success example: 0 message: type: string description: Response message example: success data: type: object required: - status - task_id - model_id properties: status: type: string enum: - pending - processing description: Task status example: pending task_id: type: string description: Unique task identifier for polling example: task-abc123 model_id: type: string description: Model ID in `provider/model` format example: skyreels/skyreels-i2v get_result: type: object description: API information to query the task result properties: method: type: string example: GET url: type: string example: https://api.modellix.ai/api/v1/tasks/task-abc123 description: Detailed data about the submitted asynchronous task. MidFrameImage: type: object required: - tag - image_url description: A mid-frame keyframe reference. properties: tag: type: string minLength: 1 pattern: ^@ description: >- Identifier starting with @, must also appear in the prompt (e.g. @image1). example: '@image1' image_url: type: string minLength: 1 description: Reference image URL (jpg/jpeg/png/gif/bmp). example: https://example.com/mid.png time_stamp: type: integer default: -1 description: Target time (seconds) of this mid-frame; -1 leaves it unspecified. example: 2 ErrorResponse: type: object required: - code - message properties: code: type: integer example: 400 message: type: string example: 'Invalid parameters: parameter ''prompt'' is required' responses: BadRequest: description: Invalid request parameters content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 400 message: 'Invalid parameters: parameter ''prompt'' is required' Unauthorized: description: Unauthorized - Invalid or missing API Key content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 401 message: 'Authentication failed: invalid API key' TooManyRequests: description: Too many requests - Rate limit exceeded headers: X-RateLimit-Limit: description: Maximum requests per minute schema: type: integer example: 100 X-RateLimit-Remaining: description: Remaining quota in current window schema: type: integer example: 0 X-RateLimit-Reset: description: Rate limit window reset time (Unix timestamp) schema: type: integer example: 1704067260 content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 429 message: >- Rate limit exceeded: 100 requests per minute, retry after 60 seconds InternalServerError: description: Internal server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 500 message: Internal server error securitySchemes: bearerAuth: type: http scheme: bearer description: 'API Key authentication. Format: `Bearer YOUR_API_KEY`.' ````