Druv King@DKing08

AI Caption Studio is an intelligent video captioning solution developed for the AMD Developer Hackathon Track 2. The application accepts a video URL or uploaded video, extracts representative key frames, and uses a multimodal vision-language model to understand the visual content before generating high-quality captions. The system produces captions in four different styles: Formal, Sarcastic, Humorous Tech, and Humorous Non-Tech, making it suitable for accessibility, content creation, social media, education, and entertainment. Instead of relying on a single prompt, the pipeline first creates a factual scene understanding and then transforms it into multiple caption styles, ensuring both accuracy and creativity. The project features an automated processing pipeline that downloads videos, extracts key frames, performs AI-based scene analysis, and returns structured caption outputs. The application is built with a modern interface for easy interaction and supports scalable deployment using Docker. The modular architecture allows future improvements such as multilingual captioning, subtitle generation, timestamped captions, and real-time video processing. Overall, AI Caption Studio demonstrates how multimodal AI can automate video understanding while generating engaging, context-aware captions for different audiences.

To participate in the hackathon, simply click Sign up with AMD. If you are not already a member of the AMD AI Developer Program (ADP), you will need to create an account. ADP members can access AI tutorials, experts, and community support. In addition, new members can claim a free month of DeepLearning.ai pro, $100 in AMD GPU cloud credits, and $50 in Fireworks AI API credits. All hackathon participants will receive on hackathon launch additional compute and API credits for their projects. Ready to build what's next on AMD? Sign up with AMD below to secure your spot.