Instructions to use Kijai/LTX2.3_comfy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use Kijai/LTX2.3_comfy with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Workflow: V2V ReTake - Recreate any section of any video
LTX-2.3 V2V ReTake - recreate any section of any video
This is based on the LTX website concept they call "Re-Take", where you can recreate a section within a video.
In other words both the start and end point for the re-take is within the input video, to essentially re-create/re-take/re-shoot part of the input video.
Works within reasonable limits (smaller edits not going too off rail hehe)
This version of this workflow is a basic one to play around with.
But I'll try update it soon where not the whole input video gets loaded, but rather just the section needed (can save a bit of memory on longer videos), and some improvements to make it easier for bigger changes
Using KJNodes LTXVAudioVideoMask to mask an area to recreate.
Feel free to try it out ;-)
https://huggingface.co/RuneXX/LTX-2.3-Workflows/