midjourney-proxy  by trueai-org

Midjourney proxy API for image/video face swaps and more

created 1 year ago
678 stars

Top 51.0% on sourcepulse

GitHubView on GitHub
Project Summary

This project provides a free, open-source API proxy for Midjourney, enabling users to integrate Midjourney's powerful image generation capabilities into their own applications. It targets developers and power users who need programmatic access to Midjourney, offering features like image blending, prompt analysis, and real-time progress tracking, with the goal of democratizing AI art creation.

How It Works

The proxy connects to Midjourney's Discord channel via WebSocket, acting as an intermediary. It intercepts user commands, processes them (including optional features like prompt translation and sensitive word detection), and sends them to Midjourney. The responses are then captured and returned to the user through the API. This approach leverages Midjourney's existing infrastructure while providing a structured API interface, supporting various Midjourney commands and account management features.

Quick Start & Requirements

  • Installation: Docker is the recommended installation method. A one-click upgrade script (docker-upgrade.sh) is provided.
    wget -O docker-upgrade.sh https://raw.githubusercontent.com/trueai-org/midjourney-proxy/main/scripts/docker-upgrade.sh && bash docker-upgrade.sh
    
  • Prerequisites: Docker, optionally MongoDB for large task volumes.
  • Resources: Requires a server environment for Docker deployment.
  • Links:

Highlighted Details

  • Supports a comprehensive set of Midjourney commands, including Imagine, Blend, Describe, Pan, Vary Region, and Zoom.
  • Features advanced account management, including multi-account support, task queue configuration, and speed mode selection (RELAX, FAST, TURBO).
  • Includes built-in functionalities like prompt translation (Baidu, GPT), sensitive word detection, and image storage options (local, CDN, OSS, R2).
  • Offers face-swapping capabilities for images and videos, with configuration for Replicate API tokens.

Maintenance & Community

The project is actively maintained, with a QQ group (565908696) for community discussion and support. The README mentions contributions from users like @如风 and @TOOM for database and account limit features.

Licensing & Compatibility

The project is licensed under the GPL protocol, permitting personal and commercial use provided copyright information is retained. It explicitly states that usage must comply with local laws and not be for illegal purposes.

Limitations & Caveats

The project notes that automatic channel joining and switching are not yet supported. Cloudflare automatic human verification is noted as only supporting Windows deployments due to browser dependencies. The free public API is limited to slow mode and relies on sponsored accounts.

Health Check
Last commit

1 day ago

Responsiveness

1 day

Pull Requests (30d)
3
Issues (30d)
2
Star History
75 stars in the last 90 days

Explore Similar Projects

Feedback? Help us improve.