anionex/banana-slides

一站式原生AI PPT生成应用,几分钟内生成一套幻灯片; 支持上传任意模板图片,上传任意素材&智能解析,一句话/大纲/页面描述自动生成PPT,口头修改指定区域、一键导出可编辑ppt、视频等 - An AI-native slides generator based on nano banana pro🍌

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 12 minutes ago
Added to GitGenius on September 1st, 2026
Created on November 29th, 2025
Open Issues & Pull Requests: 67 (-1)
GitHub issues: Enabled
Number of forks: 1,784
Total Stargazers: 15,558 (+0)
Total Subscribers: 63 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 4.7 hours
Mean response time: 6.8 days
90th percentile: 11.4 days
Tracked items: 249

How this project is maintained

Around half of the issues opened in the past year never receive a reply. Only 21% of issues opened in the past year have been closed. Three people close 92% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 12
New in 7 days: 2
Closed in 7 days: 1
Avg open age: 179 days
Stale 30+ days: 11
Stale 90+ days: 8

Recent activity

Opened in 7 days: 1
Closed in 7 days: 1
Comments in 7 days: 0
Events in 7 days: 7

Top labels

  • bug (33)
  • reminder (15)
  • enhancement (2)

Most active issues this week

Detailed Description

Banana Slides is an AI-native presentation generator that creates editable PowerPoint files from text prompts, outlines, documents, images, and custom templates.

The tool addresses the time-consuming nature of manual slide creation by automating layout and design through AI. Users can generate presentations from a single sentence, detailed outline, or page-by-page descriptions. The system supports uploading custom template images and materials, which it intelligently parses to inform slide generation. Once created, presentations can be edited conversationally through voice or text commands, then exported as editable PPTX files or video formats.

The project suits teams and individuals who need rapid presentation creation without design expertise. It works well for scenarios where speed matters more than pixel-perfect customization, such as quick internal briefings, educational materials, or iterative pitch decks. The tool maintains project history and supports reproducible workflows, allowing users to regenerate or refine presentations from the same inputs.

Development activity shows consistent engagement with the codebase. The project maintains comprehensive documentation including quick start guides, deployment instructions, and architecture documentation. Docker deployment is supported for self-hosting. The tool is written in TypeScript and offers both online access and a desktop application option. The README provides clear pathways for local installation, API integration, and testing, indicating active maintenance of multiple deployment modes.