🙏 Fork Notice: This project is based on hugohe3/ppt-master. Enhanced with Jimeng (即梦) self-hosted image generation support — deploy jimeng-api to generate images via your own Jimeng instance.

English | 中文

Live Demo · About Hugo He · Examples · FAQ · Contact

Official channels — this project is published only on GitHub (primary) and AtomGit (auto-synced mirror). Redistributions on any other platform are unofficial and not maintained by the author. Licensed under MIT — attribution required.

Drop in a PDF, DOCX, URL, or Markdown — get back a natively editable PowerPoint with real shapes, real text boxes, and real charts. Not images. Click anything and edit it.

Why PPT Master?

There's no shortage of AI presentation tools — what's missing is one where the output is actually usable as a real PowerPoint file. I build presentations every day, but most tools export images or web screenshots: they look nice but you can't edit anything. Others produce bare-bones text boxes and bullet lists. And they all want a monthly subscription, upload your files to their servers, and lock you into their platform.

PPT Master is different:

• Real PowerPoint — if a file can't be opened and edited in PowerPoint, it shouldn't be called a PPT. Every element PPT Master outputs is directly clickable and editable
• Transparent, predictable cost — the tool is free and open source; the only cost is your own AI editor, and you know exactly what you're paying. As low as $0.08/deck with VS Code Copilot
• Data stays local — your files shouldn't have to be uploaded to someone else's server just to make a presentation. Apart from AI model communication, the entire pipeline runs on your machine
• No platform lock-in — your workflow shouldn't be held hostage by any single company. Works with Claude Code, Cursor, VS Code Copilot, and more; supports Claude, GPT, Gemini, Kimi, and other models

See live examples → · examples/ — 15 projects, 229 pages

Magazine — warm earthy tones, photo-rich layout	Academic — structured research format, data-driven
Dark Art — cinematic dark background, gallery aesthetic	Nature Documentary — immersive photography, minimal UI
Tech / SaaS — clean white cards, pricing table layout	Product Launch — high contrast, bold specs highlight

I'm a finance professional (CPA · CPV · Consulting Engineer (Investment)) who got tired of spending hours on presentations that could be automated. So I built this.

PPT Master started from a simple frustration: existing AI slide tools export images, not editable shapes. As someone who reviews and edits hundreds of slides in investment and consulting work, that was unacceptable. I wanted real DrawingML — click on any element and change it, just like you built it by hand.

This project is my attempt to bridge the gap between domain expertise and product engineering — turning a complex professional pain point into an open-source tool that anyone can use.

🌐 Personal website · 📧 heyug3@gmail.com · 🐙 @hugohe3

You only need Python. Everything else is installed via pip install -r requirements.txt.

TL;DR — Install Python, run pip install -r requirements.txt, and you're ready to generate presentations.

# macOS
brew install python
pip install -r requirements.txt

# Ubuntu / Debian
sudo apt install python3 python3-pip
pip install -r requirements.txt

# macOS (only if the above conditions apply)
brew install node
brew install pandoc

# Ubuntu / Debian
sudo apt install nodejs npm
sudo apt install pandoc

Option A — Download ZIP (no Git required): click Code → Download ZIP on the GitHub page, then unzip.

Option B — Git clone (requires Git installed):

git clone https://github.com/hugohe3/ppt-master.git
cd ppt-master

Then install dependencies:

pip install -r requirements.txt

To update later (Option B only): python3 skills/ppt-master/scripts/update_repo.py

Provide source materials (recommended): Place your PDF, DOCX, images, or other files in the projects/ directory, then tell the AI chat panel which files to use. The quickest way to get the path: right-click the file in your file manager or IDE sidebar → Copy Path (or Copy Relative Path) and paste it directly into the chat.

You: Please create a PPT from projects/q3-report/sources/report.pdf

Paste content directly: You can also paste text content straight into the chat window and the AI will generate a PPT from it.

You: Please turn the following into a PPT: [paste your content here...]

Either way, the AI will first confirm the design spec:

AI:  Sure. Let's confirm the design spec:
     [Template] B) Free design
     [Format]   PPT 16:9
     [Pages]    8-10 pages
     ...

The AI handles everything — content analysis, visual design, SVG generation, and PPTX export.

Output: Two timestamped files are saved to exports/ — a native-shapes .pptx (directly editable) and an _svg.pptx snapshot for visual reference. Requires Office 2016+.

AI lost context? Ask it to read skills/ppt-master/SKILL.md.

Something went wrong? Check the FAQ — it covers model selection, layout issues, export problems, and more. Continuously updated from real user reports.

The image_gen.py tool supports multiple providers, but the recommended set is intentionally kept small.

• Core recommended: gemini, openai, qwen, zhipu, volcengine, jimeng
• Extended: stability, bfl (FLUX), ideogram
• Experimental: siliconflow, fal, replicate

To inspect the current support tiers in the CLI:

cp .env.example .env    # then edit with your API key

IMAGE_BACKEND=gemini                        # required — must be set explicitly
GEMINI_API_KEY=your-api-key
GEMINI_MODEL=gemini-3.1-flash-image-preview

Supported backends: gemini · openai · qwen · zhipu · volcengine · jimeng · stability · bfl · ideogram · siliconflow · fal · replicate

Run python3 skills/ppt-master/scripts/image_gen.py --list-backends to see tiers. Environment variables override .env. Use provider-specific keys (GEMINI_API_KEY, OPENAI_API_KEY, etc.) — global IMAGE_API_KEY is not supported.

export IMAGE_BACKEND=gemini
export GEMINI_API_KEY=your-api-key
export GEMINI_MODEL=gemini-3.1-flash-image-preview
python3 skills/ppt-master/scripts/image_gen.py "abstract tech background"

This is useful for CI, containers, secret managers, and one-off local runs.

Important:

• The script reads the current process environment, not your shell startup files in the abstract
• If a tool launches a non-interactive shell and your ~/.bashrc or ~/.zshrc is not sourced, those exports may not be visible
• In that situation, .env is usually the more stable local choice

💡 Provider-specific config: Put credentials and overrides in provider namespaces such as GEMINI_API_KEY, GEMINI_MODEL, GEMINI_BASE_URL, OPENAI_API_KEY, QWEN_MODEL, ZHIPU_MODEL, VOLCENGINE_API_KEY, and REPLICATE_API_TOKEN.

💡 No global image credentials: IMAGE_API_KEY, IMAGE_MODEL, and IMAGE_BASE_URL are intentionally not supported. Use provider-specific variables only.

💡 Multi-provider setup: You can keep multiple providers in one .env or environment, but IMAGE_BACKEND must explicitly select the active one.

Example:

IMAGE_BACKEND=zhipu

GEMINI_API_KEY=your-gemini-key
GEMINI_MODEL=gemini-3.1-flash-image-preview

ZHIPU_API_KEY=your-zhipu-key
ZHIPU_MODEL=glm-image

Switch providers by changing IMAGE_BACKEND only.

💡 Recommendation: Prefer the core backends unless you have a clear reason to use an extended or experimental provider.

⚠️ Prerequisite: You must deploy jimeng-api first. This is a self-hosted service that wraps the Jimeng (即梦) image generation API.

Deployment steps (Docker recommended):

git clone https://github.com/iptag/jimeng-api.git
cd jimeng-api
# Configure with your Jimeng credentials, then:
docker-compose up -d

The service runs at http://localhost:8009 by default.

Configuration example (after deployment):

IMAGE_BACKEND=jimeng
JIMENG_BASE_URL=http://192.168.10.50:8009
JIMENG_TOKEN=your-session-token  # Optional; omit if no auth required
JIMENG_MODEL=jimeng-4.5

💡 AI Image Generation Tip: For best quality, generate images in Gemini and select Download full size. Remove the watermark with gemini-watermark-remover or this project's skills/ppt-master/scripts/gemini_watermark_remover.py.

See CONTRIBUTING.md for how to get involved.

MIT

SVG Repo · Tabler Icons · Robin Williams (CRAP principles) · McKinsey, BCG, Bain

Looking to collaborate, integrate PPT Master into your workflow, or just have questions?

• 💬 Questions & sharing — GitHub Discussions
• 🐛 Bug reports & feature requests — GitHub Issues
• 📧 Business & consulting inquiries — heyug3@gmail.com
• 🌐 Learn more about the author — www.hehugo.com

If this project helps you, please give it a ⭐!

This project is based on hugohe3/ppt-master. If you find it helpful, please consider sponsoring the original author.

This project is supported by:

If this project saves you time, consider buying me a coffee!

PayPal

Alipay / 支付宝

Made with ❤️ by Hugo He

⬆ Back to Top