---
id: runware
version: "0.5.24"
license: MIT
license_treatment: permissive
maintenance: active
---

# runware — The Python Runware SDK is used to interact with the Runware API, powered by the Runware inference platform. It supports image generation, video generation, image upscale, video upscale, image caption, video caption, image background removal, video background removal, audio generation, and more. It also allows the use of an existing gallery of models or selecting any model or LoRA from the CivitAI gallery. The API also supports inpainting, outpainting, and a series of other ControlNet models.

License: permissive · Maintenance: active · Downloads: 2.6M/mo

## What it is and what it does

Runware is an async Python client for the Runware inference platform, a hosted service for AI-powered image and media operations. It wraps REST and WebSocket transports to the Runware API, letting you generate images from text or images, upscale, remove backgrounds, and apply ControlNet models—all without running inference locally. The library depends on aiofiles, httpx, python-dotenv, and websockets to handle async I/O and environment configuration.

The package is in active maintenance but marked as Alpha; the maintainers have published a newer official SDK (runware-python) that covers the full feature surface going forward. This library remains supported during the transition, so it is stable enough for production use but may not receive all new features. You interact with it by instantiating a Runware client, connecting to the API, and calling methods like imageInference() with request objects that specify prompts, models, and generation parameters.

Use it for:

- Generate images from text prompts using Stable Diffusion or other models from the CivitAI gallery.
- Upscale images or videos without local GPU resources by delegating to Runware's hosted inference.
- Remove backgrounds from images or videos as part of a batch processing pipeline.
- Apply ControlNet models or LoRA fine-tunes to customize image generation behavior.
- Integrate asynchronous image generation into web services via webhooks for long-running tasks.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Client library for the Runware inference API, enabling image generation, upscaling, background removal, and other AI-powered image operations via async Python.

Yes, if you need a straightforward async client for the Runware API and are comfortable with an Alpha-stage library. Install friction is low, maintenance is active, and there are no known vulnerabilities. Be aware that the maintainers recommend the newer runware-python SDK for new projects, so this package is best suited for existing integrations or when you specifically need this API surface. Requires a Runware account and API key to be useful.

## Install

pip install runware
uv add runware
poetry add runware

## Installing runware

Before you install: Low install friction with a pure-Python wheel and four lightweight async dependencies (aiofiles, httpx, python-dotenv, websockets). Active maintenance with a recent release 45 days ago; repository shows ongoing commits and is not archived.

License in practice: MIT license permits commercial and private use with minimal restrictions, making it suitable for most projects without legal friction.

Quickstart:

pip install runware

from runware import Runware, IImageInference

async def main():
    runware = Runware(api_key="your_key")
    await runware.connect()
    request = IImageInference(positivePrompt="sunset", model="civitai:36520@76907", height=512, width=512)
    images = await runware.imageInference(requestImage=request)
    for img in images:
        print(img.imageURL)

Requires RUNWARE_API_KEY environment variable or explicit API key; Runware account with API credentials and trial credits needed to call the service.

Verify before relying:

- Whether the package is actively receiving new features or only bug fixes during the transition to runware-python.
- Specific rate limits or quota constraints for the Runware API when using this SDK.
- Whether all inference operations (video, audio, caption) are fully functional or partially deprecated.

## Package facts

- License: MIT (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 2.6M/month (top 5,000 on PyPI)
- Known vulnerabilities: none known

## Tags

runware api client, image generation sdk, text to image python, ai image inference, stable diffusion api, image upscaling, background removal api, image-generation, async-client, hosted-inference

[View on SkillFed](https://skillfed.io/packages/runware) · [View on PyPI](https://pypi.org/project/runware/)