Dooy/chatgpt-web-midjourney-proxy

One UI is all done with chatgpt web, midjourney, gpts,suno,luma,runway,viggle,flux,ideogram,realtime,pika,udio; Simultaneous support Web / PWA / Linux / Win / MacOS platform

ChatGPT‑Web‑Midjourney‑Proxy

What it is – An open‑source web UI that combines OpenAI’s ChatGPT (including GPT‑4‑vision, Whisper, TTS, and the new gpts store) with a large collection of generative‑AI back‑ends such as Midjourney, Stable Diffusion‑style image models (Flux, DALL·E), video generators (Luma, Runway, Pika, Kling), music generators (Suno, Udio, Riffusion), dance generation (Viggle), and face‑swap via InsightFace. The UI lets you switch APIs, upload files, and use the same chat interface for text, image, audio, and video creation.

Key capabilities

  • ChatGPT chat with custom API key/base‑url, multi‑turn context, and optional image upload for GPT‑4‑vision.
  • Real‑time voice input (browser ASR) and Whisper‑based transcription, plus TTS output.
  • Direct Midjourney control: generate images, upscale, vary, in‑paint, zoom, extend canvas, mix seeds, and switch between the standard and niji bots. Works with both midjourney‑proxy and midjourney‑proxy‑plus APIs.
  • Integrated multimodal generators:
    • Audio – Udio (text‑to‑music), Suno (lyrics & style control, audio‑to‑audio).
    • Video – Luma, Runway, Pika, Kling (text‑to‑video and image‑to‑video).
    • Dance – Viggle.
    • Image – Flux, DALL·E‑3, Ideogram, plus image‑to‑image variations.
  • “GPT‑Store” (gpts) UI for swapping between custom model endpoints.
  • Local file storage via localforage; optional Cloudflare R2 or custom uploader.
  • Security features: optional password protection, brute‑force lockout, and environment‑variable based secret handling.

How to run

  1. Docker (recommended for full feature set) – Pull the image ydlhero/chatgpt-web-midjourney-proxy and provide the required environment variables (OpenAI key, Midjourney proxy URL/secret, Suno/Luma endpoints, etc.). Example command is in the README.
  2. Vercel one‑click deploy – Click the Vercel button; set OPENAI_API_BASE_URL, OPENAI_API_KEY, MJ_SERVER, and MJ_API_SECRET in the Vercel UI.
  3. Desktop/Server binary – Download the appropriate release from the GitHub releases page and run the executable with the same env‑vars.

Configuration – All behaviour is driven by environment variables. Highlights:

  • OPENAI_API_* – OpenAI endpoint and key.
  • MJ_SERVER / MJ_API_SECRET – Midjourney proxy.
  • SUNO_SERVER / SUNO_KEY – Suno music API.
  • LUMA_SERVER / LUMA_KEY – Luma video API.
  • CUSTOM_MODELS – Whitelist of extra model IDs.
  • AUTH_SECRET_* – Simple password protection and brute‑force limits.
  • UPLOAD_TYPE – Choose where uploaded files go (R2, local container, custom URL).

Who it’s for – Users who want a single browser‑based dashboard to experiment with many generative‑AI services without juggling separate front‑ends or API clients. It is also useful for developers who need a quick UI for testing prompts across text, image, audio, and video models.

License – MIT (see license file).

All details above are taken directly from the repository’s README; no additional features have been inferred.

Related

  • Project
    Angel-ML/angel

    Angel is a Java/Scala‑based distributed machine‑learning and graph‑computing platform that uses a parameter‑server architecture. It supports many classic ML algorithms (LR, SVM, GBDT, LDA*, etc.) and graph algorithms (PageRank, GCN, GraphSAGE, etc.), can run on YARN or locally, and offers a Spark integration (Spark on Angel) for easy job submission.

  • Project
    argosopentech/argos-translate

    Argos Translate is an open‑source Python library for offline neural‑machine translation. It downloads pre‑trained OpenNMT models packaged as ".argosmodel" files, supports pivoting through intermediate languages, offers GPU acceleration via CTranslate2, and can be used via a Python API, CLI, or a separate desktop GUI. The project also powers the LibreTranslate web/API service.

  • Project
    OpenSenseNova/SenseNova-U1

    OpenSenseNova’s SenseNova‑U1 series are open‑source, native‑unified multimodal models (text + image) built on the NEO‑unify architecture. They support high‑quality 4K image generation, dense‑text infographic creation, image editing, VQA, and interleaved text‑image tutorials. The repo provides training code, pre‑trained 8 B‑parameter checkpoints (including community‑quantized GGUF files), example inference scripts, and deployment guides, all under an Apache 2.0 license.

  • Project
    basketikun/infinite-canvas

    An open-source AI image creation workbench that integrates an infinite canvas, multi-modal AI generation, and agentic canvas manipulation into a single workspace.