mit-han-lab/radial-attention
Sparse attention for long video generation
View on index · View in 3D Map
Related repos
- fast attention algorithm for transformers, boosts speed and memory efficiency
- generates 4k cinematic videos from text or images
- Efficient Triton-based linear attention kernels for PyTorch and multiple hardware platforms
- Analyzes videos using vision models and Whisper
- Generates minutes-long videos from text and images
- video diffusion model for text-to-video, image-to-video, extension, and transitions
- Generates short videos from text scripts
- diffusion model for upscaling real-world videos with text prompts
- Toolkit for fine-tuning and training large language and vision models
- open-source language and vision models with huge context window and hybrid attention
