Download
FramePack explores compact representations for sequences of image frames, targeting tasks where many near-duplicate frames carry redundant information. The idea is to “pack” frames by detecting shared structure and storing differences efficiently, which can accelerate training or inference on video-like data. By reducing I/O and memory bandwidth, datasets become lighter to load while models still see the essential temporal variation. The repository demonstrates both packing and unpacking steps, making it straightforward to integrate into preprocessing pipelines. It’s useful for diffusion and generative models that learn from sequential image datasets, as well as classical pipelines that batch many related frames. With a simple API and examples, it invites experimentation on tradeoffs between compression, fidelity, and speed.
Features
- Packing and unpacking of frame sequences with minimal code changes
- Storage formats that reduce redundancy and dataset size
- Faster I/O and training throughput on video-like datasets
- Examples and scripts for integrating into preprocessing workflows
- Knobs to balance compression ratio against visual fidelity
- Applicable to diffusion training, animation datasets, and burst photography
Project Samples
