FramePack uses a laptop to easily play with AI to generate long videos

FramePack is the official implementation and desktop software for the paper “Packing Input Frame Contexts in Next-Frame Prediction Models for Video Generation,” offering a streamlined video diffusion workflow via a Gradio interface. It leverages a next-frame prediction neural network that compresses frame context into a constant length, making the generation workload independent of video duration and boosting efficiency. Even with only 6 GB of GPU memory, laptop GPUs can run the 13 B model to process thousands of frames, enabling high-quality long video production on resource-limited devices. Released under the Apache-2.0 license, the project features an active community with regular updates; FramePack-F1 was launched on May 3, 2025, delivering enhanced performance and user experience. This repository is the only official FramePack website; avoid fake domains to prevent downloading counterfeit software.

Official website：https://github.com/lllyasviel/FramePack

Note that this repo is a functional desktop software with minimal standalone high-quality sampling system and memory management.

Start with this repo before you try anything else!

Requirements:

• Nvidia GPU in RTX 30XX, 40XX, 50XX series that supports fp16 and bf16. The GTX 10XX/20XX are not tested.
• Linux or Windows operating system.
• At least 6GB GPU memory.

To generate 1-minute video (60 seconds) at 30fps (1800 frames) using 13B model, the minimal required GPU memory is 6GB. (Yes 6 GB, not a typo. Laptop GPUs are okay.)

About speed, on my RTX 4090 desktop it generates at a speed of 2.5 seconds/frame (unoptimized) or 1.5 seconds/frame (teacache). On my laptops like 3070ti laptop or 3060 laptop, it is about 4x to 8x slower. Troubleshoot if your speed is much slower than this.

In any case, you will directly see the generated frames since it is next-frame(-section) prediction. So you will get lots of visual feedback before the entire video is generated.