FRAMEPACK
// Lets make video diffusion practical!
FramePack
Lets make video diffusion practical!
13EmergingUnknown
What it does
Official implementation and desktop software for "Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models". Links: Paper, Project Page FramePack is a next-frame (next-frame-section) prediction neural network structure that generates videos progressively. FramePack compresses input contexts to a constant length so that the generation workload is invariant to
Getting Started
git
git clone https://github.com/lllyasviel/FramePack