I built Lungo, a tool that generates image-based slideshows and UGC-style videos using AI. The system creates visuals and assembles them into structured, shareable content based on a text prompt.
What it does:
• Generates images from prompts using a custom diffusion model
• Constructs slideshows or short-form videos with transitions and optional voiceover
• Handles layout, text generation, and multi-language support
• Outputs are consistent in resolution and format, ready for distribution
I built with a React, firebase, OpenAI, Runway and ffmpeg. Feedback and questions welcome.
I built Lungo, a tool that generates image-based slideshows and UGC-style videos using AI. The system creates visuals and assembles them into structured, shareable content based on a text prompt.
What it does: • Generates images from prompts using a custom diffusion model • Constructs slideshows or short-form videos with transitions and optional voiceover • Handles layout, text generation, and multi-language support • Outputs are consistent in resolution and format, ready for distribution
I built with a React, firebase, OpenAI, Runway and ffmpeg. Feedback and questions welcome.