FoundationVision/FlashVideo
A diffusion-based text-to-video generation model that efficiently produces high-resolution videos from text prompts.
Not currently ranked — collecting fresh signals.
star history
FlashVideo is a high-resolution video generation model based on diffusion architecture. It uses a two-stage approach: first generating low-resolution video from text prompts, then upscaling to high resolution with minimal computation. The system targets efficient inference through flow-based matching and progressive resolution refinement.
Frequently asked
- What is FoundationVision/FlashVideo?
- A diffusion-based text-to-video generation model that efficiently produces high-resolution videos from text prompts.
- Is FlashVideo open source?
- Yes — FoundationVision/FlashVideo is open source, released under the Apache-2.0 license.
- What language is FlashVideo written in?
- FoundationVision/FlashVideo is primarily written in Python.
- How popular is FlashVideo?
- FoundationVision/FlashVideo has 460 stars on GitHub.
- Where can I find FlashVideo?
- FoundationVision/FlashVideo is on GitHub at https://github.com/FoundationVision/FlashVideo.