Skip to content

Pixano-Inference Documentation

multimodal

pixano/pixano-inference

Pixano-Inference Documentation

pixano/pixano-inference

Home
Pixano
Pixano-Inference
Pixano-Inference
- Home
  Home
- Getting Started
  Getting Started
- API reference
  API reference
  - celery
  - client
  - data
    data
    
    read_vector_databases
  - main
  - models
    models
    
    base
    
    sam2
    
    transformers
    
    vllm
  - providers
    providers
    
    base
    
    registry
    
    sam2
    
    transformers
    
    utils
    
    vllm
  - pydantic
    pydantic
    
    base
    
    data
    data
    
    vector_database
    
    models
    
    nd_array
    
    tasks
    tasks
    
    image
    image
    
    mask_generation
    
    utils
    
    zero_shot_detection
    
    multimodal
    multimodal
    
    conditional_generation
    
    video
    video
    
    mask_generation
  - routers
    routers
    
    app
    
    providers
    
    tasks
    tasks
    
    image
    
    multimodal
    
    nlp
    
    tasks
    
    video
    
    utils
  - settings
  - tasks
    tasks
    
    image
    
    multimodal multimodal
    Table of contents
    
    MultimodalImageNLPTask
    
    nlp
    
    task
    
    utils
    
    video
  - utils
    utils
    
    media
    
    package
    
    url
    
    vector

`pixano_inference.tasks.multimodal`

Multimodal tasks.

`MultimodalImageNLPTask`

Bases: Task

Multimodal tasks.