Generate AI videos and images, all from one place
Xenon Studio is a web app I built to bring several AI video and image models together in a single interface, using each service's official API.
Heads up: I've stopped working on this project, so it's no longer maintained.
Jumping between different dashboards every time you want to use a new AI model gets frustrating fast. Xenon Studio was my attempt to fix that: one clean interface where you can pick a model, write your prompt, and get your video or image back.
Everything runs through the official APIs, so you're talking directly to the providers, with no middlemen in between.
| Provider | Model | Type |
|---|---|---|
| BytePlus | Seedance 2.5 | Video |
| Kling | Kling 3.0 | Video |
| Gemini | Omini Flash 1.1 | Video |
| Gemini | Nano Banana 2 | Image |
| Gemini | Nano Banana 2 Pro | Image |
All of these worked well for me (except Google Omini Flash 1.1) when I used valid API keys from each provider's official platform. You'll need your own keys to try them.
| Layer | Technology |
|---|---|
| Backend | Django |
| Task Queue | Celery |
| Broker / Cache | Redis |
| Frontend | Django Templates, Tailwind CSS |
Video generation can take a while for Complex scenes and Prompts, so I didn't want the app to freeze while you wait. Requests are handed off to Celery workers in the background, with Redis keeping the queue moving, so the interface stays responsive the whole time.
If you're looking for a starting point for your own AI studio, Run it yourself with your own API keys, you're welcome to fork this and make it yours.
What you could do with this?
- Plug in your own API keys for BytePlus, Kling, and Gemini
- Add new models or swap out the ones that are here
- Give it your own look, branding, and change the Internals to match your Workflow
Each provider has its own pricing and usage limits, Subject to that provider's terms and pricing.
Xenon Studio