3 results found Sort:
Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model
Created
2024-11-27
82 commits to main branch, last one 25 days ago
Context parallel attention that accelerates DiT model inference with dynamic caching
Created
2024-10-28
187 commits to main branch, last one 16 hours ago
Text Encoders finally matter 🤖🎥 - scale CLIP & LLM influence! + a Nerdy Transformer Shuffle node
Created
2024-12-16
18 commits to CLIP-vision branch, last one about a month ago