> ## 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.

# Seedance 2.0 Mini I2V

> [Core Function] Seedance 2.0 Mini I2V is the lightweight multimodal image-to-video variant. [Strengths] Supports 480p/720p, 24 fps, 4-15s MP4 output, with optional first/last frame, reference images, and audio references. [Routing] Use for cost-efficient image-to-video.



## OpenAPI

````yaml /model-api/bytedance/bytedance-i2v.json post /bytedance/seedance-2.0-mini-i2v
openapi: 3.1.0
info:
  description: The image-to-video models API from ByteDance.
  version: 1.0.0
  contact:
    name: Modellix Support
    email: support@modellix.ai
  title: ByteDance Image-to-Video Models API
servers:
  - url: https://api.modellix.ai/api/v1
    description: The image-to-video models API from ByteDance.
security:
  - bearerAuth: []
paths:
  /bytedance/seedance-2.0-mini-i2v:
    post:
      summary: Seedance 2.0 Mini I2V
      description: >-
        [Core Function] Seedance 2.0 Mini I2V is the lightweight multimodal
        image-to-video variant. [Strengths] Supports 480p/720p, 24 fps, 4-15s
        MP4 output, with optional first/last frame, reference images, and audio
        references. [Routing] Use for cost-efficient image-to-video.
      operationId: seedance20MiniI2vAsync
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/Seedance20MiniI2vRequest'
            examples:
              frame_mode:
                summary: Frame mode — first frame
                value:
                  prompt: The person smiles and waves at the camera
                  first_frame_image: https://example.com/first.jpg
                  duration: 5
                  resolution: 720p
              frame_mode_start_end:
                summary: Frame mode — first and last frame
                value:
                  prompt: Smooth transition from the first frame to the last frame
                  first_frame_image: https://example.com/first.jpg
                  last_frame_image: https://example.com/last.jpg
                  duration: 10
                  resolution: 720p
              reference_mode:
                summary: Reference mode — images + audio
                value:
                  prompt: Motion follows [Audio 1], style from [Image 1]
                  reference_images:
                    - https://example.com/ref.jpg
                  audio_urls:
                    - https://example.com/ref.mp3
                  duration: 8
                  resolution: 720p
      responses:
        '200':
          description: Task submitted successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AsyncTaskResponse'
components:
  schemas:
    Seedance20MiniI2vRequest:
      description: >-
        Seedance 2.0 Mini image-to-video. Same options as Fast 2.0 I2V;
        `resolution` is limited to 480p/720p. **Note:** images containing real
        human faces are not supported per [BytePlus Seedance 2.0
        API](https://docs.byteplus.com/en/docs/ModelArk/1520757).
      oneOf:
        - $ref: '#/components/schemas/Seedance20I2vFrameOption720'
          title: Option 1 — Frame mode
          description: First-frame or first-to-last-frame animation.
        - $ref: '#/components/schemas/Seedance20I2vReferenceOption720'
          title: Option 2 — Reference mode
          description: Multimodal reference images with optional audio.
    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
              example: task-abc123
            model_id:
              type: string
              description: Model ID
              example: model-123
            get_result:
              type: object
              description: API information to query the task result
              properties:
                method:
                  type: string
                  description: HTTP method
                  example: GET
                url:
                  type: string
                  description: Full URL to query the task result
                  example: https://api.modellix.ai/api/v1/tasks/task-abc123
          description: Detailed data about the submitted asynchronous task.
    Seedance20I2vFrameOption720:
      type: object
      description: >-
        First-frame or first-to-last-frame animation. Do not pass
        `reference_images`.
      required:
        - first_frame_image
      properties:
        prompt:
          type: string
          minLength: 1
          maxLength: 10000
          description: >-
            Optional. Video description. Maximum 10000 characters. Recommended
            prompt length: under 1000 words. Frame animation description.
          example: The person smiles and waves at the camera
        first_frame_image:
          type: string
          minLength: 1
          description: Required. Starting frame URL or Base64.
          example: https://example.com/first.jpg
        last_frame_image:
          type: string
          minLength: 1
          description: Optional. Ending frame URL or Base64. Requires `first_frame_image`.
          example: https://example.com/last.jpg
        audio_urls:
          type: array
          minItems: 1
          maxItems: 3
          description: >-
            Optional. Up to 3 reference audio URLs. Use `[Audio n]` placeholders
            in prompt.
          items:
            type: string
            minLength: 1
            description: Audio URL.
        ratio:
          type: string
          enum:
            - '21:9'
            - '16:9'
            - '4:3'
            - '1:1'
            - '3:4'
            - '9:16'
          default: '16:9'
          description: Aspect ratio of the generated video.
        duration:
          type: integer
          enum:
            - 4
            - 5
            - 6
            - 7
            - 8
            - 9
            - 10
            - 11
            - 12
            - 13
            - 14
            - 15
          default: 5
          description: Video duration in seconds (4-15 seconds).
        seed:
          type: integer
          minimum: -1
          maximum: 4294967295
          default: -1
          description: Random seed for reproducible generation. Use -1 for random.
        camera_fixed:
          type: boolean
          default: false
          description: Whether to keep the camera fixed during generation.
        generate_audio:
          type: boolean
          default: true
          description: Whether to generate audio.
        execution_expires_after:
          type: integer
          default: 172800
          minimum: 3600
          maximum: 259200
          description: Task expiration time in seconds.
        return_last_frame:
          type: boolean
          default: false
          description: Whether to return the last frame of the generated video.
        resolution:
          type: string
          enum:
            - 480p
            - 720p
          default: 720p
          description: Output resolution of the video.
    Seedance20I2vReferenceOption720:
      type: object
      description: >-
        Multimodal reference images (and optional audio). Do not pass
        `first_frame_image` or `last_frame_image`.
      required:
        - reference_images
      properties:
        prompt:
          type: string
          minLength: 1
          maxLength: 10000
          description: >-
            Optional. Video description. Maximum 10000 characters. Recommended
            prompt length: under 1000 words. Use `[Image n]` and `[Audio n]`
            when referencing inputs.
          example: The person smiles and waves at the camera
        reference_images:
          type: array
          minItems: 1
          maxItems: 9
          description: >-
            Required. 1–9 reference image URLs. Use `[Image n]` placeholders in
            prompt.
          items:
            type: string
            minLength: 1
            description: Image URL or Base64 data.
          example:
            - https://example.com/ref.jpg
        audio_urls:
          type: array
          minItems: 1
          maxItems: 3
          description: >-
            Optional. Up to 3 reference audio URLs. Use `[Audio n]` placeholders
            in prompt.
          items:
            type: string
            minLength: 1
            description: Audio URL.
        ratio:
          type: string
          enum:
            - '21:9'
            - '16:9'
            - '4:3'
            - '1:1'
            - '3:4'
            - '9:16'
          default: '16:9'
          description: Aspect ratio of the generated video.
        duration:
          type: integer
          enum:
            - 4
            - 5
            - 6
            - 7
            - 8
            - 9
            - 10
            - 11
            - 12
            - 13
            - 14
            - 15
          default: 5
          description: Video duration in seconds (4-15 seconds).
        seed:
          type: integer
          minimum: -1
          maximum: 4294967295
          default: -1
          description: Random seed for reproducible generation. Use -1 for random.
        camera_fixed:
          type: boolean
          default: false
          description: Whether to keep the camera fixed during generation.
        generate_audio:
          type: boolean
          default: true
          description: Whether to generate audio.
        execution_expires_after:
          type: integer
          default: 172800
          minimum: 3600
          maximum: 259200
          description: Task expiration time in seconds.
        return_last_frame:
          type: boolean
          default: false
          description: Whether to return the last frame of the generated video.
        resolution:
          type: string
          enum:
            - 480p
            - 720p
          default: 720p
          description: Output resolution of the video.
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: 'API Key authentication. Format: `Bearer YOUR_API_KEY`.'

````