
Deploy Banana Slides
AI presentation generator: prompt, outline or doc to slides (Gemini/OpenAI)
Banana Slides
Just deployed
Banana Slides Backend
Just deployed
/data
Deploy and Host Banana Slides on Railway
Banana Slides is an open-source (AGPL-3.0) AI presentation generator. You give it a one-line idea, an outline or page descriptions, optionally with reference documents and a style template image, and it writes the outline, generates every slide as an image with Gemini or an OpenAI-compatible model, lets you edit pages by prompt, and exports PPTX or PDF.
About Hosting Banana Slides
This template runs Banana Slides v0.4.0 as two services built from this repo, with the official upstream images pinned by digest. The backend (Flask) keeps its SQLite database and every upload and generated slide on a Railway volume, and runs the database migrations on each start. The public web service is nginx: it serves the React app, proxies the API over Railway's private network, and puts the whole UI behind a login with a generated password, because Banana Slides has no accounts of its own and its Settings page holds your AI API key. After deploy, open the URL, sign in, and add your API key under Settings.
Common Use Cases
- Turn a one-line idea or an outline into a complete slide deck
- Re-style a document or report as slides that follow your own template image
- Edit individual slides by prompt and export the result as PPTX or PDF
Dependencies for Banana Slides Hosting
- An API key for Google Gemini (default) or for any OpenAI-compatible endpoint that serves text and image models
- A Railway volume for the SQLite database, uploads and generated slides (included)
Deployment Dependencies
- Banana Slides source: https://github.com/Anionex/banana-slides
- Template repo: https://github.com/aalfath/banana-slides-railway-template
- Google AI Studio API keys: https://aistudio.google.com/apikey
Implementation Details
Services in this template:
- Banana Slides (public): nginx on
PORT8080. It serves the UI, proxies/apiand/filesto the backend, and requires the loginadminwith the password in itsBASIC_AUTH_PASSWORDvariable (generated at deploy; read it in the service's Variables tab)./healthanswers without login for Railway's health check. - Banana Slides Backend (private): the Flask API on port 5000, listening on IPv6 for Railway's private network. Its volume at
/dataholdsinstance/database.dbanduploads/.SECRET_KEYis generated at deploy.
After deploy:
- Open the public URL and sign in as
adminwith the generatedBASIC_AUTH_PASSWORD. - Open Settings, choose the provider format (Gemini or OpenAI), enter your API key (and API base URL if you use a proxy or another OpenAI-compatible service), and pick the text and image models. Settings are stored in the database on the volume, so they survive redeploys.
- Optional: set the output language in Settings (the upstream default is Chinese), and add a MinerU token for parsing PDFs and Office files, or a Baidu OCR key for editable PPTX export.
You can also set GOOGLE_API_KEY, or AI_PROVIDER_FORMAT=openai with OPENAI_API_KEY and OPENAI_API_BASE, as variables on the backend service. They seed the settings on the first start only.
Updates: this template builds from the GitHub repo above, so when the pinned version is bumped, Railway shows an "update available" notice on your project and you choose when to apply it. Read CHANGELOG.md in the repo first.
Why Deploy Banana Slides on Railway?
Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it.
By deploying Banana Slides on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway.
Template Content
Banana Slides
aalfath/banana-slides-railway-templateBanana Slides Backend
aalfath/banana-slides-railway-template
