BudgetPixel Alibaba API

openapi: 3.2.0
info:
  title: Budgetpixel Alibaba API
  version: '2026-06-20'
  contact:
    email: support@budgetpixel.com
    name: BudgetPixel Support
  description: 'Operations tagged Alibaba across 2 of this provider''s published API definitions: budgetpixel-openapi.yaml, budgetpixel-openapi.yaml. Each path carries the servers of the definition it was published in.'
servers:
- description: Production
  url: https://api.budgetpixel.com/v1
security:
- ApiKeyAuth: []
tags:
- name: Alibaba
paths:
  /images/qwen-image:
    post:
      description: 'Alibaba Qwen-Image — best-in-class complex text rendering and typography. Text-to-image with seed control.


        **Asynchronous.** Returns a job `id` (the image is not in this response). Poll [`GET /v1/images/{id}`](/api-reference/images/get-image-job-status) until `status` is `succeeded` — the generated image URLs are in that response''s `images` array (each `{ url, position }`).'
      operationId: createImage_qwen_image
      requestBody:
        content:
          application/json:
            schema:
              properties:
                aspect_ratio:
                  default: '1:1'
                  description: Output aspect ratio.
                  enum:
                  - '1:1'
                  - '16:9'
                  - '9:16'
                  - '21:9'
                  - '9:21'
                  - '4:3'
                  - '3:4'
                  - '3:2'
                  - '2:3'
                  type: string
                num_images:
                  default: 1
                  description: Number of images to generate.
                  maximum: 4
                  minimum: 1
                  type: integer
                prompt:
                  description: Text description of the image to generate.
                  type: string
                seed:
                  description: Seed for reproducible generation. Omit for random.
                  type: integer
              required:
              - prompt
              type: object
        required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateImageResponse'
          description: Job accepted.
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '429':
          $ref: '#/components/responses/TooManyRequests'
      summary: Generate image with Qwen-Image
      tags:
      - Alibaba
    servers:
    - description: Production
      url: https://api.budgetpixel.com/v1
  /images/qwen-image-2.0:
    post:
      description: 'Alibaba Qwen Image 2.0 — fast unified generation and editing with strong text rendering and multi-image fusion from up to 3 reference images.


        **Asynchronous.** Returns a job `id` (the image is not in this response). Poll [`GET /v1/images/{id}`](/api-reference/images/get-image-job-status) until `status` is `succeeded` — the generated image URLs are in that response''s `images` array (each `{ url, position }`).'
      operationId: createImage_qwen_image_2_0
      requestBody:
        content:
          application/json:
            schema:
              properties:
                aspect_ratio:
                  default: '1:1'
                  description: Output aspect ratio.
                  enum:
                  - '1:1'
                  - '16:9'
                  - '9:16'
                  - '4:3'
                  - '3:4'
                  - '3:2'
                  - '2:3'
                  - '21:9'
                  - match_input_image
                  type: string
                negative_prompt:
                  description: What to avoid in the generated image.
                  type: string
                num_images:
                  default: 1
                  description: Number of images to generate.
                  maximum: 4
                  minimum: 1
                  type: integer
                prompt:
                  description: Text description of the image to generate.
                  type: string
                reference_images:
                  description: Optional reference images (up to 3) for image editing and multi-image fusion. Each item is a public image URL, a data URI, raw base64, or an uploaded-file URL from POST /v1/uploads. Omit for text-to-image. Use aspect_ratio "match_input_image" to keep the input's aspect ratio.
                  items:
                    type: string
                  maxItems: 3
                  type: array
                seed:
                  description: Seed for reproducible generation. Omit for random.
                  type: integer
                size:
                  default: 1.5K
                  description: Output resolution tier.
                  enum:
                  - 1K
                  - 1.5K
                  - 2K
                  type: string
              required:
              - prompt
              type: object
        required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateImageResponse'
          description: Job accepted.
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '429':
          $ref: '#/components/responses/TooManyRequests'
      summary: Generate image with Qwen Image 2.0
      tags:
      - Alibaba
    servers:
    - description: Production
      url: https://api.budgetpixel.com/v1
  /images/qwen-image-2.0-pro:
    post:
      description: 'Alibaba Qwen Image 2.0 Pro — premium generation with enhanced text rendering, fine-grained realism, and stronger semantic adherence. Multi-image fusion from up to 3 reference images.


        **Asynchronous.** Returns a job `id` (the image is not in this response). Poll [`GET /v1/images/{id}`](/api-reference/images/get-image-job-status) until `status` is `succeeded` — the generated image URLs are in that response''s `images` array (each `{ url, position }`).'
      operationId: createImage_qwen_image_2_0_pro
      requestBody:
        content:
          application/json:
            schema:
              properties:
                aspect_ratio:
                  default: '1:1'
                  description: Output aspect ratio.
                  enum:
                  - '1:1'
                  - '16:9'
                  - '9:16'
                  - '4:3'
                  - '3:4'
                  - '3:2'
                  - '2:3'
                  - '21:9'
                  - match_input_image
                  type: string
                negative_prompt:
                  description: What to avoid in the generated image.
                  type: string
                num_images:
                  default: 1
                  description: Number of images to generate.
                  maximum: 4
                  minimum: 1
                  type: integer
                prompt:
                  description: Text description of the image to generate.
                  type: string
                reference_images:
                  description: Optional reference images (up to 3) for image editing and multi-image fusion. Each item is a public image URL, a data URI, raw base64, or an uploaded-file URL from POST /v1/uploads. Omit for text-to-image. Use aspect_ratio "match_input_image" to keep the input's aspect ratio.
                  items:
                    type: string
                  maxItems: 3
                  type: array
                seed:
                  description: Seed for reproducible generation. Omit for random.
                  type: integer
                size:
                  default: 1.5K
                  description: Output resolution tier.
                  enum:
                  - 1K
                  - 1.5K
                  - 2K
                  type: string
              required:
              - prompt
              type: object
        required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateImageResponse'
          description: Job accepted.
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '429':
          $ref: '#/components/responses/TooManyRequests'
      summary: Generate image with Qwen Image 2.0 Pro
      tags:
      - Alibaba
    servers:
    - description: Production
      url: https://api.budgetpixel.com/v1
  /images/qwen-image-3.0:
    post:
      description: 'Alibaba Qwen Image 3.0 — unified generation and editing balancing quality and speed, with multi-image fusion from up to 3 reference images. Billing: 40 credits per image at 1K, 45 at 2K.


        **Asynchronous.** Returns a job `id` (the image is not in this response). Poll [`GET /v1/images/{id}`](/api-reference/images/get-image-job-status) until `status` is `succeeded` — the generated image URLs are in that response''s `images` array (each `{ url, position }`).'
      operationId: createImage_qwen_image_3_0
      requestBody:
        content:
          application/json:
            schema:
              properties:
                aspect_ratio:
                  default: '1:1'
                  description: Output aspect ratio.
                  enum:
                  - '1:1'
                  - '16:9'
                  - '9:16'
                  - '4:3'
                  - '3:4'
                  - '3:2'
                  - '2:3'
                  - '21:9'
                  - match_input_image
                  type: string
                negative_prompt:
                  description: What to avoid in the generated image.
                  type: string
                num_images:
                  default: 1
                  description: Number of images to generate.
                  maximum: 4
                  minimum: 1
                  type: integer
                prompt:
                  description: Text description of the image to generate.
                  type: string
                reference_images:
                  description: Optional reference images (up to 3) for image editing and multi-image fusion. Each item is a public image URL, a data URI, raw base64, or an uploaded-file URL from POST /v1/uploads. Omit for text-to-image. Use aspect_ratio "match_input_image" to keep the input's aspect ratio.
                  items:
                    type: string
                  maxItems: 3
                  type: array
                seed:
                  description: Seed for reproducible generation. Omit for random.
                  type: integer
                size:
                  default: 1K
                  description: Output resolution tier. 1K bills 40 credits per image; 2K bills 45.
                  enum:
                  - 1K
                  - 2K
                  type: string
              required:
              - prompt
              type: object
        required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateImageResponse'
          description: Job accepted.
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '429':
          $ref: '#/components/responses/TooManyRequests'
      summary: Generate image with Qwen Image 3.0
      tags:
      - Alibaba
    servers:
    - description: Production
      url: https://api.budgetpixel.com/v1
  /images/qwen-image-3.0-pro:
    post:
      description: 'Alibaba Qwen Image 3.0 Pro — professional infographics, exquisite photorealism, and stronger prompt adherence. Multi-image fusion from up to 3 reference images. Billing: 45 credits per image at 1K, 85 at 2K.


        **Asynchronous.** Returns a job `id` (the image is not in this response). Poll [`GET /v1/images/{id}`](/api-reference/images/get-image-job-status) until `status` is `succeeded` — the generated image URLs are in that response''s `images` array (each `{ url, position }`).'
      operationId: createImage_qwen_image_3_0_pro
      requestBody:
        content:
          application/json:
            schema:
              properties:
                aspect_ratio:
                  default: '1:1'
                  description: Output aspect ratio.
                  enum:
                  - '1:1'
                  - '16:9'
                  - '9:16'
                  - '4:3'
                  - '3:4'
                  - '3:2'
                  - '2:3'
                  - '21:9'
                  - match_input_image
                  type: string
                negative_prompt:
                  description: What to avoid in the generated image.
                  type: string
                num_images:
                  default: 1
                  description: Number of images to generate.
                  maximum: 4
                  minimum: 1
                  type: integer
                prompt:
                  description: Text description of the image to generate.
                  type: string
                reference_images:
                  description: Optional reference images (up to 3) for image editing and multi-image fusion. Each item is a public image URL, a data URI, raw base64, or an uploaded-file URL from POST /v1/uploads. Omit for text-to-image. Use aspect_ratio "match_input_image" to keep the input's aspect ratio.
                  items:
                    type: string
                  maxItems: 3
                  type: array
                seed:
                  description: Seed for reproducible generation. Omit for random.
                  type: integer
                size:
                  default: 1K
                  description: Output resolution tier. 1K bills 45 credits per image; 2K bills 85.
                  enum:
                  - 1K
                  - 2K
                  type: string
              required:
              - prompt
              type: object
        required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateImageResponse'
          description: Job accepted.
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '429':
          $ref: '#/components/responses/TooManyRequests'
      summary: Generate image with Qwen Image 3.0 Pro
      tags:
      - Alibaba
    servers:
    - description: Production
      url: https://api.budgetpixel.com/v1
  /images/wan-2.7:
    post:
      description: 'Alibaba Wan 2.7 — image generation and editing with thinking mode, multi-reference composition from up to 9 reference images, and up to 2K output.


        **Asynchronous.** Returns a job `id` (the image is not in this response). Poll [`GET /v1/images/{id}`](/api-reference/images/get-image-job-status) until `status` is `succeeded` — the generated image URLs are in that response''s `images` array (each `{ url, position }`).'
      operationId: createImage_wan_2_7
      requestBody:
        content:
          application/json:
            schema:
              properties:
                aspect_ratio:
                  default: '1:1'
                  description: Output aspect ratio.
                  enum:
                  - '1:1'
                  - '16:9'
                  - '9:16'
                  - '4:3'
                  - '3:4'
                  - '3:2'
                  - '2:3'
                  - '21:9'
                  - match_input_image
                  type: string
                num_images:
                  default: 1
                  description: Number of images to generate.
                  maximum: 4
                  minimum: 1
                  type: integer
                prompt:
                  description: Text description of the image to generate.
                  type: string
                reference_images:
                  description: Optional reference images (up to 9) for image editing and multi-reference composition. Each item is a public image URL, a data URI, raw base64, or an uploaded-file URL from POST /v1/uploads. Omit for text-to-image. Use aspect_ratio "match_input_image" to keep the input's aspect ratio.
                  items:
                    type: string
                  maxItems: 9
                  type: array
                seed:
                  description: Seed for reproducible generation. Omit for random.
                  type: integer
                size:
                  default: 2K
                  description: Output resolution tier.
                  enum:
                  - 1K
                  - 2K
                  type: string
                thinking_mode:
                  description: Enable the model's thinking mode for stronger prompt planning. Text-to-image only — ignored when reference images are provided.
                  type: boolean
              required:
              - prompt
              type: object
        required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateImageResponse'
          description: Job accepted.
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '429':
          $ref: '#/components/responses/TooManyRequests'
      summary: Generate image with Wan 2.7
      tags:
      - Alibaba
    servers:
    - description: Production
      url: https://api.budgetpixel.com/v1
  /images/wan-2.7-pro:
    post:
      description: 'Alibaba Wan 2.7 Pro — professional edition of Wan 2.7 with 4K output support, thinking mode, and multi-reference composition from up to 9 reference images.


        **Asynchronous.** Returns a job `id` (the image is not in this response). Poll [`GET /v1/images/{id}`](/api-reference/images/get-image-job-status) until `status` is `succeeded` — the generated image URLs are in that response''s `images` array (each `{ url, position }`).'
      operationId: createImage_wan_2_7_pro
      requestBody:
        content:
          application/json:
            schema:
              properties:
                aspect_ratio:
                  default: '1:1'
                  description: Output aspect ratio.
                  enum:
                  - '1:1'
                  - '16:9'
                  - '9:16'
                  - '4:3'
                  - '3:4'
                  - '3:2'
                  - '2:3'
                  - '21:9'
                  - match_input_image
                  type: string
                num_images:
                  default: 1
                  description: Number of images to generate.
                  maximum: 4
                  minimum: 1
                  type: integer
                prompt:
                  description: Text description of the image to generate.
                  type: string
                reference_images:
                  description: Optional reference images (up to 9) for image editing and multi-reference composition. Each item is a public image URL, a data URI, raw base64, or an uploaded-file URL from POST /v1/uploads. Omit for text-to-image. Use aspect_ratio "match_input_image" to keep the input's aspect ratio.
                  items:
                    type: string
                  maxItems: 9
                  type: array
                seed:
                  description: Seed for reproducible generation. Omit for random.
                  type: integer
                size:
                  default: 2K
                  description: Output resolution tier. 4K applies to text-to-image only — with reference images the output falls back to 2K.
                  enum:
                  - 1K
                  - 2K
                  - 4K
                  type: string
                thinking_mode:
                  description: Enable the model's thinking mode for stronger prompt planning. Text-to-image only — ignored when reference images are provided.
                  type: boolean
              required:
              - prompt
              type: object
        required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateImageResponse'
          description: Job accepted.
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '429':
          $ref: '#/components/responses/TooManyRequests'
      summary: Generate image with Wan 2.7 Pro
      tags:
      - Alibaba
    servers:
    - description: Production
      url: https://api.budgetpixel.com/v1
  /images/z-image-turbo:
    post:
      description: 'Tongyi-MAI Z-Image-Turbo — ultra-fast 6B-parameter text-to-image with only 9 inference steps. Supports negative prompt and seed control.


        **Asynchronous.** Returns a job `id` (the image is not in this response). Poll [`GET /v1/images/{id}`](/api-reference/images/get-image-job-status) until `status` is `succeeded` — the generated image URLs are in that response''s `images` array (each `{ url, position }`).'
      operationId: createImage_z_image_turbo
      requestBody:
        content:
          application/json:
            schema:
              properties:
                aspect_ratio:
                  default: '1:1'
                  description: Output aspect ratio.
                  enum:
                  - '1:1'
                  - '16:9'
                  - '9:16'
                  - '4:3'
                  - '3:4'
                  - '3:2'
                  - '2:3'
                  - '21:9'
                  - '9:21'
                  type: string
                negative_prompt:
                  description: What to avoid in the generated image.
                  type: string
                num_images:
                  default: 1
                  description: Number of images to generate.
                  maximum: 4
                  minimum: 1
                  type: integer
                prompt:
                  description: Text description of the image to generate.
                  type: string
                seed:
                  description: Seed for reproducible generation. Omit for random.
                  type: integer
              required:
              - prompt
              type: object
        required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateImageResponse'
          description: Job accepted.
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '429':
          $ref: '#/components/responses/TooManyRequests'
      summary: Generate image with Z-Image-Turbo
      tags:
      - Alibaba
    servers:
    - description: Production
      url: https://api.budgetpixel.com/v1
  /videos/happyhorse-1.1:
    post:
      description: 'Alibaba HappyHorse 1.1 — highly realistic dynamic rendering. Text-to-video; image-to-video (start frame only); and reference-images-to-video (up to 9 images for subject-consistent generation). 720p or 1080p, priced per resolution (see `resolution_pricing` in GET /v1/models); 4–15 seconds. Audio is determined by the model (no toggle). No video-edit mode.


        **Asynchronous.** Returns a job `id` (the video is not in this response). Poll [`GET /v1/videos/{id}`](/api-reference/videos/get-video-job-status) until `status` is `succeeded` — the video URL is in that response''s `video_url`.'
      operationId: createVideo_happyhorse_1_1
      requestBody:
        content:
          application/json:
            schema:
              properties:
                aspect_ratio:
                  default: '16:9'
                  description: Aspect ratio. Ignored when a start image already sets the frame.
                  enum:
                  - '16:9'
                  - '9:16'
                  - '1:1'
                  - '4:3'
                  - '3:4'
                  type: string
                image:
                  description: Optional start frame for image-to-video. Provide a public image URL, a data URI, raw base64, or an uploaded-file URL from POST /v1/uploads. Omit for text-to-video. Can't be combined with `reference_images`.
                  type: string
                length_seconds:
                  default: 5
                  description: Video length in seconds (4–15).
                  maximum: 15
                  minimum: 4
                  type: integer
                prompt:
                  description: Text description of the video.
                  type: string
                reference_images:
                  description: Optional reference images (1–9) for subject-consistent reference-to-video. Each item is a public image URL, a data URI, raw base64, or an uploaded-file URL from POST /v1/uploads. Can't be combined with `image` (the start frame).
                  items:
                    type: string
                  maxItems: 9
                  type: array
                resolution:
                  default: 720p
                  description: Output resolution. Pricing varies by resolution — see `resolution_pricing` in GET /v1/models.
                  enum:
                  - 720p
                  - 1080p
                  type: string
              required:
              - prompt
              type: object
        required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateVideoResponse'
          description: Job accepted.
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '429':
          $ref: '#/components/responses/TooManyRequests'
      summary: Generate video with HappyHorse 1.1
      tags:
      - Alibaba
    servers:
    - description: Production
      url: https://api.budgetpixel.com/v1
  /videos/wan-2.7-video:
    post:
      description: 'Alibaba Wan 2.7 (video) — text-to-video; image-to-video with a start frame and an optional end frame; and video editing (supply a `video`). Prompt-driven narrative, optional generated audio, and an optional driving-audio track. 720p or 1080p, priced per resolution (see `resolution_pricing` in GET /v1/models); 5, 10, or 15 seconds. Video editing instead takes its length from the input clip (`length_seconds` and `aspect_ratio` are ignored) and bills the INPUT duration on top of the output at the same per-second rate — so a 10s clip costs 20 seconds'' worth; estimate via POST /v1/cost. (The Wan 2.7 image model is `wan-2.7` under POST /v1/images.)


        **Asynchronous.** Returns a job `id` (the video is not in this response). Poll [`GET /v1/videos/{id}`](/api-reference/videos/get-video-job-status) until `status` is `succeeded` — the video URL is in that response''s `video_url`.'
      operationId: createVideo_wan_2_7_video
      requestBody:
        content:
          application/json:
            schema:
              properties:
                aspect_ratio:
                  default: '16:9'
                  description: Aspect ratio. Ignored when a start image or an input `video` already sets the frame.
                  enum:
                  - '16:9'
                  - '9:16'
                  - '1:1'
                  - '4:3'
                  - '3:4'
                  type: string
                audio:
                  description: Optional driving-audio track (MP3/WAV/OGG) for the generated video. Provide a public audio URL or an uploaded-file URL from POST /v1/uploads (passed by URL, not inlined). Ignored when `generate_audio` is false.
                  type: string
                end_image:
                  description: Optional end frame, used together with `image` (the start frame) to interpolate the video between the two frames. Same input forms as `image`.
                  type: string
                generate_audio:
                  default: true
                  description: Generate audio with the video (default true; no price impact).
                  type: boolean
                image:
                  description: Optional start frame for image-to-video. Provide a public image URL, a data URI, raw base64, or an uploaded-file URL from POST /v1/uploads. Omit for text-to-video. Can't be combined with `video`.
                  type: string
                length_seconds:
                  default: 5
                  description: Video length in seconds. Ignored for video editing, which inherits the input clip's length.
                  enum:
                  - 5
                  - 10
                  - 15
                  type: integer
                prompt:
                  description: Text description of the video, or the edit instruction when `video` is supplied (for example "change the video to an 8-bit pixel style").
                  type: string
                reference_images:
                  description: Optional reference images (up to 4, free) used only with `video` — they guide the edit, for example supplying the person or style to apply to the clip. Each item is a public image URL, a data URI, raw base64, or an uploaded-file URL from POST /v1/uploads.
                  items:
                    type: string
                  maxItems: 4
                  type: array
                resolution:
                  default: 720p
                  description: Output resolution. Pricing varies by resolution — see `resolution_pricing` in GET /v1/models.
                  enum:
                  - 720p
                  - 1080p
                  type: string
                video:
                  description: 'Optional input video to edit (2-15s, MP4/MOV, ≤100MB). Supplying it switches the request to video editing: the model applies `prompt` to this clip. Provide a public video URL or an uploaded-file URL from POST /v1/uploads (videos are passed by URL, not inlined). Billed on the INPUT duration at the full per-second rate in addition to the output — estimate via POST /v1/cost. Can''t be combined with `image`/`end_image`.'
                  type: string
              required:
              - prompt
              type: object
        required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateVideoResponse'
          description: Job accepted.
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '429':
          $ref: '#/components/responses/TooManyRequests'
      summary: Generate video with Wan 2.7
      tags:
      - Alibaba
    servers:
    - description: Production
      url: https://api.budgetpixel.com/v1
  /videos/wan-3.0-video:
    post:
      description: 'Alibaba Wan 3.0 — all-in-one video generation up to 30 seconds at 30fps. Text-to-video; image-to-video (first + optional last frame); and reference-to-video mixing up to 10 reference images, up to 5 reference video clips (15s combined) for editing/replication/extension, and up to 5 reference audio clips (15s combined). In reference mode the p

# --- truncated at 32 KB (45 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/budgetpixel/refs/heads/main/openapi/budgetpixel-alibaba-api-openapi.yml