🔥 Latest Updates

• [2026-08-20]: Release Candidate 4 of v0.9.0 is available, fixing unavailable LazyLLM online providers (qwen etc.) and missing SOCKS proxy dependencies in desktop builds, restoring the previous-step button to return to the description editor, and fixing export task dialog occlusion and desktop property drawer interaction; One-click download and install
• [2026-08-20]: The preview page restores the "Previous Step" button, letting you return to the description editor from the slide preview with one click
• [2026-08-20]: Fixed the export task dialog being occluded by the page properties drawer; the desktop drawer now expands by default and adapts to the window width
• [2026-07-31]: Desktop builds now register all 11 LazyLLM online providers (qwen / doubao / deepseek / glm / kimi / minimax / sensenova / siliconflow / ppio / aiping / openai), fixing the "Unsupported source: qwen" error in packaged apps
• [2026-08-06]: Release Candidate 3 of v0.9.0 is available, with major fixes for Volcengine Agent Plans configuration and credential recovery, plus isolated outline streams, in-place slide editing, field contract v2, template matching, and editable PPTX export improvements; One-click download and install
• [2026-07-15]: Custom outline/description requirement presets now automatically repair corrupted browser cache, retaining valid presets to prevent abnormal cache from blocking the editing page
• [2026-07-11]: Release Candidate 2 of v0.9.0 is released, containing all capabilities of RC1, and fixing the inconsistent MinerU directory for editable PPTX on Windows desktop, and incorrect FFprobe path for explanation videos; One-click download and install
• [2026-06-23]: Page-by-page templates launched — supports two modes: unified template / independent templates per page. You can upload images or PDFs to build a project template library. AI automatically parses template styles and intelligently matches them to each page with one click, or you can manually bind them page by page. Dual modes can be toggled bi-directionally at any time (Documentation)
• [2026-04-25]: Asset Toolbox launched — adds three new modes based on the original asset generation: full-image editing, box-selection editing (overlay/replace), and smart erase, offering a unified entry point and one-stop operation
• [2026-04-25]: Supports binding accounts via OpenAI official OAuth login. After binding, Codex can be used directly as a text/image generation provider without manually entering the API Key. Plus accounts can generate 100+ 2k images in five hours (Tutorial) (based on OpenAI's official OAuth PKCE authorization flow, non-reverse-engineered)
• [2026-04-25]: Supports saving custom text style description templates, which can be named, color-coded, and persistently reused, eliminating the need to re-enter them every time
• [2026-04-23]: Added support for the gpt-image-2 model. Meanwhile, the export effect of editable backgrounds has been improved due to model capability upgrades (select Generative Acquisition in Settings - Export Options - Background Acquisition)
• [2026-04-11]: Added support for CLI operations and integrated agent skills
• [2026-03]: Added several features and optimizations, such as extra fields, multi-aspect ratio settings, etc.
• [2026-02-09]: New Features and Optimizations
  • New Features
    • Supports pasting images directly into the homepage, outline, and description cards for instant recognition, providing a better interactive experience.
    • Manual outline section editing: Supports manually adjusting the section (part) to which a page belongs.
    • Docker multi-architecture: Images now support amd64 / arm64 builds.
    • Internationalization + Dark Mode: Added Chinese/English switching; supports light/dark/system-matching themes; dark mode compatibility for all components.
  • Bug Fixes & UX Optimizations
    • Fixed export-related 500 errors, reference file association timing, outline/page data misalignment, task polling for incorrect projects, infinite polling in description generation, memory leaks in image preview, and handling of partial failures in batch deletion.
    • Optimized formatting example tips, HTTP error message copy, modal closing experience, cleaned up localStorage for old projects, and removed redundant prompts for first-time project creation.
    • Several other optimizations and fixes.

✨ Project Origin

Have you ever found yourself in this dilemma: the presentation is due tomorrow, but your slides are still completely blank; you have countless brilliant ideas in your head, but all your enthusiasm is drained by tedious layout and design?

We yearn to quickly create presentations that are both professional and visually appealing. Although traditional AI PPT generation apps generally meet the need for "speed," they still suffer from the following issues:

• 1️⃣ You can only choose from preset templates, with no flexibility to adjust styles.
• 2️⃣ Low degree of freedom, making multi-round revisions difficult to carry out.
• 3️⃣ The final products look very similar, resulting in severe homogenization.
• 4️⃣ Low asset quality and a lack of relevance.
• 5️⃣ Fragmented text-image layouts and a poor design aesthetic.

These shortcomings make it difficult for traditional AI PPT generators to simultaneously satisfy our two core requirements: speed and aesthetics. Even if they claim to be "Vibe PPT," they are still far from being truly "Vibe" in my eyes.

However, the emergence of the nano banana🍌 model has turned things around. I tried using 🍌pro to generate slide pages and found that the results were exceptional in terms of quality, aesthetics, and consistency. Additionally, it could render almost all the text requested in the prompt with high precision while faithfully following the style of the reference image. So, why not build a native "Vibe PPT" application based on 🍌pro?

👨‍💻 Applicable Scenarios

1. Beginners: Quickly generate beautiful PPTs with zero barrier to entry, no design experience required, reducing the hassle of choosing templates
2. PPT Professionals: Reference AI-generated layouts and combinations of text and graphic elements to quickly gain design inspiration
3. Educators: Quickly convert teaching content into illustrated lesson plan PPTs to enhance classroom effectiveness
4. Students: Quickly complete assignment presentations, focusing energy on content rather than layout and beautification
5. Professionals: Quickly visualize business proposals and product introductions, with rapid adaptation to multiple scenarios

🎯Goal: Lower the barrier to PPT creation, enabling everyone to quickly create beautiful and professional presentations

🎨 Result Examples

See more at Use Cases

🎯 Features

1. Flexible and Diverse Creation Paths

Supports three starting modes—Idea, Outline, and Page Description—to accommodate different creative habits.

• One-Sentence Generation: Enter a topic, and AI automatically generates a well-structured outline and page-by-page content descriptions.
• Natural Language Editing: Supports modifying the outline or descriptions using natural language in "Vibe" style (e.g., "Change page three to a case study"), with AI responding and adjusting in real-time.
• Outline/Description Mode: Supports both one-click batch generation and manual adjustment of details.

2. Powerful Asset Parsing Capabilities

• Multi-Format Support: Upload files such as PDF, Docx, MD, and Txt, and the background system will automatically parse the content.
• Smart Extraction: Automatically identify key points, image links, and chart information within the text to provide rich materials for generation.
• Automatic Image Storage: Images extracted from the documents will automatically enter the project's asset library once the reference files are associated with the project, allowing for direct reuse in the future.
• Style Reference: Supports uploading reference images or templates to customize the PPT style.

3. "Vibe"-style Natural Language Modification

No longer limited by complex menu buttons, directly issue edit commands using natural language.

• Partial Redraw: Make conversational edits to unsatisfactory areas (e.g., "change this chart to a pie chart").
• Full-page Optimization: Generate high-definition, stylistically consistent pages based on nano banana pro🍌.

4. Out-of-the-box Format Export

• Multi-format Support: One-click export to standard PPTX or PDF files.
• Playback Settings: Enable slide transitions before exporting to PPTX, supporting classic effects like fade-in and fade-out.
• Perfect Fit: Default 16:9 aspect ratio, no need for secondary layout adjustments, ready for direct presentation.

5. Freely Editable PPTX Export (Beta under iteration)

• Export images to high-fidelity, clean-background PPT slides with freely editable images and text
• See related updates at https://github.com/Anionex/banana-slides/issues/121

6. One-click Export of Explanation Videos

• One-click conversion of slides to presentation videos (MP4) with AI voiceovers and subtitles
• AI automatically generates natural spoken voiceovers based on slide descriptions and content
• Supports configuring multiple delivery styles, multiple languages, and various voices

🌟 Comparison with NotebookLM Slide Deck Feature

Feature	NotebookLM	This Project
Page Limit	15 pages	Unlimited
Post-editing	Prompt-based modification	Box-selection editing + verbal editing
Adding Assets	Cannot add after generation	Freely add after generation
Export Formats	Supports exporting as PDF, (non-editable image) PPTX	Export as PDF, (image or editable) PPTX, presentation video
Watermark	Watermark in free version	No watermark, freely add or delete elements

Note: As new features are added, this comparison may become outdated.

🗺️ Roadmap

Status	Milestone
✅ Completed	Add more assets to a single PPT slide
✅ Completed	Vibe verbal editing of selected areas on a single PPT slide
✅ Completed	Asset module: Asset generation, uploading, etc.
✅ Completed	Support uploading + parsing of multiple file formats
✅ Completed	Support Vibe verbal adjustment of outlines and descriptions
✅ Completed	Initial support for exporting editable PPTX files
🔄 In progress	Support exporting editable PPTX with multi-layer, precise cutout
🔄 In progress	Web search
🔄 In progress	Agent mode
✅ Completed	TTS narration video export (Chinese/English/Japanese multiple voices, subtitles)

📦 Usage

(New) One-click Deployment Using App Templates

This is the simplest way, requiring no Docker installation or project downloading. You can access the application directly after creation.

1. Deploy and start this application with one click via RainYun (High bandwidth, suitable for HD image generation and downloading. Free trial available for new users)

• Graphic Tutorial

2. Stay tuned

Using Docker Compose🐳

Quickly start front-end and back-end services using Docker Compose.

📒 Windows/Mac User Guide

If you are using Windows or macOS, please first install Docker Desktop, and ensure that Docker is running (Windows users can check the system tray icon; macOS users can check the menu bar icon), then follow the same steps in the documentation.

Tip: If you encounter issues, Windows users should enable the WSL 2 backend in the Docker Desktop settings (recommended); also ensure that ports 3011 and 5011 are not occupied.

0. Clone the repository

git clone https://github.com/Anionex/banana-slides
cd banana-slides

1. Configure environment variables

Create the .env file (refer to .env.example):

cp .env.example .env

(Optional, can also be configured in the user interface after startup) Edit the .env file to configure the required environment variables.

2. Start Services

⚡ Using Pre-built Images (Recommended)

docker compose -f docker-compose.prod.yml up -d

Image names:

• anoinex/banana-slides-frontend:latest
• anoinex/banana-slides-backend:latest

Build images from scratch

docker compose up -d

3. Access the Application

• Frontend: http://localhost:3011
• Backend API: http://localhost:5011

4. View Logs

docker logs --tail 200 banana-slides-backend
docker logs -f --tail 100 banana-slides-backend
docker logs --tail 100 banana-slides-frontend

5. Stop Services

docker compose down

6. Update Project

Using pre-built images (docker-compose.prod.yml)

docker compose -f docker-compose.prod.yml pull
docker compose -f docker-compose.prod.yml up -d

Using local build (docker-compose.yml)

git pull
docker compose down
docker compose build --no-cache
docker compose up -d

Deploy from Source

Environment Requirements

• Python 3.10 or higher
• uv - Python package manager
• Node.js 16+ and npm
• FFmpeg - Required for explanation video export, and must include support for libass / ass subtitle filters
• A valid Google Gemini API key
• (Optional) LibreOffice - Required when uploading PPTX files using the "PPT Refurbish" feature to convert PPTX to PDF

Backend Installation

git clone https://github.com/Anionex/banana-slides
cd banana-slides

Install uv:

curl -LsSf https://astral.sh/uv/install.sh | sh

Install dependencies and configure the .env file according to the project documentation.

Frontend Installation

cd frontend
npm install

Start Backend Service

cd backend
uv run alembic upgrade head && uv run python app.py

The backend service will start at http://localhost:5011.

Start the Frontend Development Server

cd frontend
npm run dev

The frontend development server will start at http://localhost:3011.

🛠️ Technical Architecture

Frontend Technology Stack

React 18 + TypeScript + Vite 5 + Zustand

Backend Technology Stack

Python 3.10+ + Flask 3.0 + uv + SQLite

Communication Group

Welcome to suggest new features or share feedback in the group.

Welcome to follow the author's social media for project updates and AI-related information.

🔧 FAQ

Please refer to the official documentation.

You can also ask questions directly on DeepWiki.

🤝 Contributing Guide

Welcome to contribute to this project through Issues and Pull Requests!

Important: Please read CONTRIBUTING.md before contributing.

📄 License

This project is open-sourced under the GNU Affero General Public License v3.0 (AGPL-3.0). It can be freely used for non-commercial purposes such as personal learning, research, experimentation, education, or non-profit scientific research activities.

For questions or cooperation inquiries, please contact: davidyang042@gmail.com

🚀 Sponsor

Acknowledgements

• Project Contributors:

• Linux.do: A new ideal community

Sponsor

Open source is not easy 🙏 If this project is valuable to you, you are welcome to buy the developer a coffee ☕️

📈 Project Statistics