PromptClip

PromptClip ✄

Create video clips using LLM prompts
?Report a Bug · Suggest a Feature

PromptClip: Create Instant Video Clips with LLM Prompts ?

What does it do? ?

It allows any developer to:

• Upload a video from any source (Local Files, Youtube, S3 etc.)
• ? Prompt that video in natural language with queries like Show funny moments in the video or find the moments useful for social media trailer
• ?️ Use any LLM of your choice like OpenAI, Claude or Gemeni Pro.
• ? Instantly watch the clip of those moments.
• Finetune the clip or supercut by ranking results, managing length of the clip etc.
• ? Add music or image overlay to the clip.

---

Results ?

Checkout these prompts and the results ?

Original Video	Prompt	Link
Shark Tank	Find every moment where a deal was offered	watch
Useful Gadgets	Show me moments in the video where the host discusses or reveals the pricing of the gadgets	watch
Sponsorship Details of Huberman Podcast	Find details about every sponsor	watch
Highlights from Masterchef Episode	Show me the feedback from every judge	watch
Important Topics/Advice from a Lecture	Find sentences where anxiety is discussed	watch
Tech Review Video	Find sentences where host explains about the battery	watch
Travel Video	What are some popular tourist destinations in Sri Lanka	watch

How do I use it?

• Get your API key: Sign up on VideoDB console (Free for the first 50 uploads, no credit card required). ?
• Set VIDEO_DB_API_KEY: Enter your key in the env file.
• Set OPENAI_API_KEY or ANTHROPIC_KEY: Add your LLM API Key in the env file.
• Install dependencies: Run pip install -r requirements.txt in your terminal.
• Run locally: Run the notebook PromptClip_text.ipynb, PromptClip_visual.ipynb and PromptClip_multimodal.ipynb to experiment with your prompts and ranking of results.

---

Roadmap ?️

1. Add support for music generation models to jazzup the cuts.
2. Integrate with other projects like Pika Labs and Midjourney.

---

Contributing ?

Your contributions make the open-source community an incredible place for learning, inspiration, and creativity. We welcome and appreciate your input! Here's how you can contribute:

• Open issues to share your use cases.
• Participate in brainstorming solutions for our roadmap.
• Suggest improvements to the codebase.

Contribution Steps

1. Fork the Project ?
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request ?

---