AetherStudio is a premium, open-source web interface designed to control Google Cloud Vertex AI's state-of-the-art image and video generation models (Imagen 4.0 and Veo 2.0/3.1). It connects a React/Vite frontend dashboard to a Node.js Express API proxy.
- 🖼️ Imagen 4.0 Integration: Text-to-image synthesis with custom aspect ratios, sample counts, and reference image upload (with configurable Subject vs. Style reference types).
- 🎥 Veo 2.0/3.1 Integration: Asynchronous text-to-video synthesis using Vertex AI Long Running Operations (LRO) with progress tracking.
- ⚡ Gemini Prompt Optimizer: Native prompt-enhancement tool powered by
gemini-2.5-flashwith built-in art-style presets (Cinematic Noir, Cyberpunk, Photorealistic, 3D Render, etc.). - 🔄 Batch Queue Manager: Queue up multiple prompts to be processed sequentially to respect Vertex AI rate limits.
- 🎬 FFmpeg Video Stitcher: Select consecutive video clips in the Media Library and stitch them into a single movie file (requires
ffmpegon the host). - 📂 Interactive Media Library: Inspect generated files, download high-res files, set images as reference targets, or delete files directly.
- Node.js: Ensure Node.js (v18+) is installed.
- Google Cloud Project: You need an active Google Cloud Project with the Vertex AI API enabled.
- FFmpeg (Optional, for video stitching):
- Linux:
sudo apt-get install ffmpeg - macOS:
brew install ffmpeg - Windows:
choco install ffmpeg
- Linux:
AetherStudio utilizes Google Application Default Credentials (ADC). It does not store or hardcode private keys.
- Install the Google Cloud CLI on your local machine.
- Authenticate your local environment by running:
gcloud auth application-default login
- This logs you in locally. The backend server automatically detects these credentials.
-
Clone the Repository:
git clone https://github.com/madonessbeat/AetherStudio.git cd AetherStudio -
Install Dependencies: Install all dependencies for both frontend and backend:
# Install root & backend dependencies npm install # Install frontend dependencies cd frontend && npm install cd ..
-
Environment Variables: Copy the environment variables template in the backend:
cp backend/.env.example backend/.env
Open
backend/.envand replaceyour-gcp-project-idwith your Google Cloud Project ID.
From the root project directory, start both the frontend and backend simultaneously:
npm run devThis starts:
- Backend Proxy: http://localhost:5000
- Frontend Dashboard: http://localhost:5173
Open http://localhost:5173 in your browser and start synthesizing!
- No API keys or credential JSON files are committed to this repository (safeguarded via
.gitignore). - All synthesis calls are proxied securely through the local Express server.
- Authentication is tied directly to the host machine running the proxy.
This project is licensed under the MIT License - see the LICENSE file for details.