lexigram-multimedia-image

Image generation for the Lexigram Framework — local and API-based backends (local-http, stability, openai, comfyui).

Overview

lexigram-multimedia-image generates still images from a text prompt. The default backend calls a local HTTP reference server (http://localhost:5005) so the package works out of the box with no API keys; hosted backends (Stability AI, OpenAI) and ComfyUI workflows are selectable via config.

Full documentation: docs.lexigram.dev

Install

uv add lexigram-multimedia-image
# Optional extras
uv add "lexigram-multimedia-image[stability]"  # Stability AI API
uv add "lexigram-multimedia-image[openai]"     # OpenAI images API

Quick Start

from lexigram import Application
from lexigram.di.module import Module, module
from lexigram.multimedia.image import ImageModule
from lexigram.contracts.multimedia import ImageProvider, ImageRequest


@module(imports=[ImageModule.configure()])
class AppModule(Module):
    pass


async def main() -> None:
    async with Application.boot(modules=[AppModule]) as app:
        image = await app.container.resolve(ImageProvider)
        result = await image.generate(ImageRequest(prompt="a cozy cabin in the snow"))
        if result.is_ok():
            asset = result.unwrap()  # MediaAsset — image bytes or URI


if __name__ == "__main__":
    import asyncio

    asyncio.run(main())

Configuration

Zero-config usage: Call ImageModule.configure() with no arguments to use the local-http backend at http://localhost:5005.

Option 1 — YAML file

# application.yaml
multimedia:
  image:
    backend: "stability"
    comfyui_base_url: "http://localhost:8188"

Option 2 — Profiles + Environment Variables

export LEX_PROFILE=production
export LEX_MULTIMEDIA__IMAGE__BACKEND=openai
export LEX_MULTIMEDIA__IMAGE__OPENAI_MODEL=dall-e-3

Option 3 — Python

from lexigram.multimedia.image import ImageModule
from lexigram.multimedia.image.config import ImageConfig

ImageModule.configure(config=ImageConfig(backend="openai", openai_model="dall-e-3"))

Config reference

Module Factory Methods

Key Features

• Four backends — local-http, stability, openai, comfyui
• ComfyUI workflows — custom workflow JSON with checkpoint, steps, and CFG scale
• Secret-managed API keys — provider keys resolved by name through the secrets backend
• Result-based — generate() -> Result[MediaAsset, MultimediaError]; errors are domain values, not exceptions

Testing

from lexigram import Application
from lexigram.multimedia.image import ImageModule


async def test_boot():
    async with Application.boot(modules=[ImageModule.stub()]) as app:
        assert app.container is not None

Key Source Files