Apps Page Background Image
Workflows/Framepack I2V - Longer videos keeping context between frames!

Framepack I2V - Longer videos keeping context between frames!

Save it for me
Operate
@
EnragedAntelope
04/22/2025
ComfyUI
Popular & HOT
Video Generation
Creative Exploration
Hunyuan Video
1 / 0
Detailed Introduction

FramePack Image to Video (I2V)

Super easy to use! All setup and optimizations have been completed for you. Just drop in your image and a good prompt indicating what you want to animate!

This includes a custom fine-tuned Hunyuan model with better prompt adherence and less censorship than the original.

Use at least ULTRA for best experience.

Thanks to Kijai for making an excellent wrapper to get this working in comfy:  https://github.com/kijai/ComfyUI-FramePackWrapper


More info from  https://github.com/lllyasviel/FramePack:

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 video length.

FramePack can process a very large number of frames with 13B models even on laptop GPUs.

FramePack can be trained with a much larger batch size, similar to the batch size for image diffusion training.

Video diffusion, but feels like image diffusion.


Details
APPComfyUI(v0.3.28)
Update Time04/22/2025
File Space15.3 GB
Models0
Extensions8
About This Template

Insanely easy high quality Image to Video, keeping context between frames to allow for much longer coherent videos than possible up to this point!