chatgpt-web-midjourney-proxy  by Dooy

One-UI for multimodal AI tasks

created 1 year ago
6,322 stars

Top 8.3% on sourcepulse

GitHubView on GitHub
Project Summary

This project provides a unified web interface for multiple AI services, including ChatGPT, Midjourney, Suno, Luma, Runway, and others. It targets users who want a single, convenient platform to access and manage various generative AI tools, offering a consolidated experience for text generation, image creation, video synthesis, and music production.

How It Works

The application acts as a proxy and frontend aggregator, integrating with backend APIs for each supported AI service. It leverages a modular architecture, allowing for the addition of new AI models and functionalities. Key features include local storage for images via localforage, support for different Midjourney bots, and advanced Midjourney operations like inpainting, zooming, and extending. The frontend is designed for cross-platform compatibility, supporting Web, PWA, Linux, Windows, and macOS.

Quick Start & Requirements

  • Installation: Download latest release from releases or use Docker.
  • Prerequisites: Requires backend proxy services for Midjourney, Suno, and Luma. Recommended to use a unified proxy service that supports multiple AI models.
  • Setup: Configuration involves setting environment variables for API keys and server URLs.
  • Demo: vercel.ddaiai.com

Highlighted Details

  • Supports a wide array of AI services: Udio, Pika, Kling, Ideogram, Runway, Viggle, Flux, Suno, ChatGPT (including GPTs, vision, TTS, Whisper), and Midjourney.
  • Advanced Midjourney features: local redraw, zoom, extension, image-to-text, and support for different Midjourney bots.
  • Cross-platform compatibility: Web, PWA, Linux, Win, macOS.
  • Customization options for ChatGPT: custom API keys, base URLs, models, context, and reply counts.

Maintenance & Community

The project is actively developed by Dooy. Links to community support or roadmaps are not explicitly provided in the README.

Licensing & Compatibility

  • License: MIT License.
  • Compatibility: Free for open-source learning use. No paid services or official groups are offered.

Limitations & Caveats

The project relies on external proxy services for many of its functionalities, which need to be set up separately. Vercel deployment does not support R2 storage. Security features like brute-force protection are primarily for Docker deployments.

Health Check
Last commit

1 week ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
7
Star History
205 stars in the last 90 days

Explore Similar Projects

Starred by Chip Huyen Chip Huyen(Author of AI Engineering, Designing Machine Learning Systems), Pietro Schirano Pietro Schirano(Founder of MagicPath), and
1 more.

SillyTavern by SillyTavern

3.2%
17k
LLM frontend for power users
created 2 years ago
updated 3 days ago
Feedback? Help us improve.