Read the Case Study | Launch The Workshop at Google AI Studio
A node editor for creating images, video, and music through precise prompting and the power of the Gemini API.
This project is designed for AI enthusiasts, educators, and creative developers looking to master multimodal generation through a visual node-based interface without writing a single line of code.
This contains everything you need to run your app locally.
View your app in AI Studio: https://ai.studio/apps/86bab6a1-d48b-4330-a9ce-bdf203db125a
Prerequisites: Node.js
- Install dependencies:
npm install - Set the
GEMINI_API_KEYin .env.local to your Gemini API key - Run the app:
npm run dev
Gemini API Image Generation Docs
Precision image synthesis using the Nano Banana (Imagen) models.
- Image / File Upload: Generate high-quality images from text prompts or use existing images as references.
- Model Selection: Choose between Nano Banana 2 (3.1 Flash) and Nano Banana Pro for different quality and speed requirements.
- Aspect Ratio & Resolution: Fine-tune the output with specific aspect ratios (from 1:1 to 16:9) and resolutions up to 4K.
Advanced video synthesis and manipulation powered by Google VEO.
- Frames to Video: Transform a sequence of images into a coherent video animation.
- Video Lite (Veo 3.1 Lite): Quick video generation for rapid prototyping and short clips.
- References to Video: Use multiple reference images to guide the style and content of your video generation.
- Extend Video: Lengthen existing video clips while maintaining temporal consistency and style.
Gemini API Music Generation Docs
High-fidelity music and audio synthesis using the Lyria 3 family of models.
- Lyria 3: Generate high-quality, 48kHz stereo audio from text prompts or images.
- Clip vs. Pro: Support for short 30-second clips (Lyria 3 Clip) or full-length songs with complex structures like verses and choruses (Lyria 3 Pro).
- Multimodal Inspiration: Use up to 10 reference images to influence the mood, genre, and instrumentation of the generated audio.