modelslab_py 0.2.1

ModelsLab's Official Python SDK

ModelsLab Python SDK

Official Python SDK for ModelsLab API - Generate AI content including images, videos, audio, 3D models, and more.

Installation

pip install modelslab_py

For async support:

pip install 'modelslab_py[async]'

Create a client

from modelslab_py.core.client import Client

client = Client(api_key="your_api_key")

Features

• Image Generation and Editing
• Video Generation
• Audio Processing
• 3D Model Generation
• Interior Design
• Deepfake Operations
• Community Models Integration

Usage Examples

Image Editing

from modelslab_py.core.client import Client
from modelslab_py.core.apis.image_editing import Image_editing
from modelslab_py.schemas.image_editing import BackgroundRemoverSchema

client = Client(api_key="your_api_key")
api = Image_editing(client=client, enterprise=False)

schema = BackgroundRemoverSchema(
    image="https://example.com/image.jpg",
    base64=False
)

response = api.background_remover(schema=schema)
print(response)

Video Generation

from modelslab_py.core.apis.video import Video
from modelslab_py.schemas.video import Text2Video

client = Client(api_key="your_api_key")
api = Video(client=client, enterprise=False)

schema = Text2Video(
    model_id="zeroscope",
    prompt="a cat walking in a garden",
    num_frames=30
)

response = api.text_to_video(schema=schema)
print(response)

Interior Design

from modelslab_py.core.apis.interior import Interior
from modelslab_py.schemas.interior import InteriorSchema

client = Client(api_key="your_api_key")
api = Interior(client=client, enterprise=False)

schema = InteriorSchema(
    prompt="modern minimalist bedroom",
    init_image="https://example.com/room.jpg"
)

response = api.interior(schema=schema)
print(response)

Audio Processing

from modelslab_py.core.apis.audio import Audio
from modelslab_py.schemas.audio import Text2Speech

client = Client(api_key="your_api_key")
api = Audio(client=client, enterprise=False)

schema = Text2Speech(
    prompt="Hello, welcome to ModelsLab",
    voice_id="madison",
    language="english"
)

response = api.text_to_speech(schema=schema)
print(response)

3D Generation

from modelslab_py.core.apis.three_d import Three_D
from modelslab_py.schemas.threed import Text23D

client = Client(api_key="your_api_key")
api = Three_D(client=client, enterprise=False)

schema = Text23D(
    prompt="a wooden chair",
    model_id="meshy-4",
    output_format="obj"
)

response = api.text_to_3d(schema=schema)
print(response)

Community Models

from modelslab_py.core.apis.community import Community
from modelslab_py.schemas.community import Text2Image

client = Client(api_key="your_api_key")
api = Community(client=client, enterprise=False)

schema = Text2Image(
    prompt="a beautiful landscape",
    model_id="midjourney",
    width=512,
    height=512
)

response = api.text_to_image(schema=schema)
print(response)

Async/Await Support

All API methods have async equivalents. Use them for concurrent requests and better performance.

Async Example with Concurrent Requests

import asyncio
from modelslab_py.core.client import Client
from modelslab_py.core.apis.video import Video
from modelslab_py.schemas.video import Text2Video

schema1 = Text2Video(
    model_id="wan2.2",
    prompt="a cat walking",
    num_frames=25,
    fps=16
)

schema2 = Text2Video(
    model_id="wan2.2",
    prompt="a dog running",
    num_frames=25,
    fps=16
)

async def main():
    async with Client(api_key="your_api_key") as client:
        api = Video(client=client, enterprise=False)

        # Run both requests concurrently
        results = await asyncio.gather(
            api.async_text_to_video(schema=schema1),
            api.async_text_to_video(schema=schema2),
        )

        print(results)

asyncio.run(main())

Async Method Naming Convention

For any synchronous method, prefix with async_:

• text_to_video() → async_text_to_video()
• text_to_image() → async_text_to_image()
• background_remover() → async_background_remover()

Provider-Based API Usage

The SDK includes provider-specific implementations for easy access to various AI models:

Minimax Provider (Video Generation)

from modelslab_py.core.client import Client
from modelslab_py.providers import MinimaxProvider
from modelslab_py.providers.minimax.schemas import Hailuo23T2VSchema

client = Client(api_key="your_api_key")
minimax = MinimaxProvider(client=client)

schema = Hailuo23T2VSchema(
    prompt="A sunset aerial shot of a lone rider galloping across a snow-covered plain"
)

response = minimax.hailuo_23_t2v(schema=schema)
print(response)

BFL Provider (Image Generation)

from modelslab_py.providers import BFLProvider
from modelslab_py.providers.bfl.schemas import FluxPro11Schema

client = Client(api_key="your_api_key")
bfl = BFLProvider(client=client)

schema = FluxPro11Schema(
    prompt="A futuristic cityscape at sunset with flying cars",
    width=1024,
    height=768
)

response = bfl.flux_pro_11(schema=schema)
print(response)

KlingAI Provider (Video Generation)

from modelslab_py.providers import KlingAIProvider
from modelslab_py.providers.klingai.schemas import KlingV25TurboT2VSchema

client = Client(api_key="your_api_key")
kling = KlingAIProvider(client=client)

schema = KlingV25TurboT2VSchema(
    prompt="Cinematic drone shot of a luxury cruise ship sailing",
    duration="5",
    aspect_ratio="16:9"
)

response = kling.kling_v25_turbo_t2v(schema=schema)
print(response)

Sync Provider (Lip Sync)

from modelslab_py.providers import SyncProvider
from modelslab_py.providers.sync.schemas import Lipsync2Schema

client = Client(api_key="your_api_key")
sync = SyncProvider(client=client)

schema = Lipsync2Schema(
    init_video="https://example.com/video.mp4",
    init_audio="https://example.com/audio.mp3"
)

response = sync.lipsync_2(schema=schema)
print(response)

Available Providers

• AlibabaProvider: Wan2.5 video generation models
• BFLProvider: Flux Pro image generation models
• BytePlusProvider: SeeDream, SeeDance, and Omni Human models
• ElevenLabsProvider: Text-to-speech and audio generation
• GoogleProvider: Imagen models for image generation
• InworldProvider: Text-to-speech with voice cloning
• KlingAIProvider: Kling video generation models
• MinimaxProvider: Hailuo video generation models
• OpenAIProvider: Sora video generation
• RunwayProvider: Gen-4 image and video models
• SonautoProvider: Music and song generation
• SyncProvider: Video lip-sync models

API Categories

• Image Editing: Background removal, super resolution, inpainting, outpainting
• Video: Text-to-video, image-to-video, watermark removal
• Audio: Text-to-speech, voice conversion, music generation
• Interior: Room design, floor planning, object placement
• 3D: Text-to-3D, image-to-3D model generation
• Deepfake: Face swapping, video manipulation
• Community: Access to community-trained models

Documentation

For detailed documentation, visit docs.modelslab.com

Support

• Discord: Join our community
• Twitter: @ModelsLabAI
• GitHub: ModelsLab

License

See LICENSE file for details.