Important Notice
Optimized to work with the latest version of ComfyUI (v0.18.1 + Frontend 1.42.8).
The latent upscaler ltx-2.3-spatial-upscaler-x2-1.1 has been released.
Version 1.0 had an issue where a strange overlay appeared at the end when generating long videos (241F+), but this has been fixed in 1.1.
Updating is strongly recommended.
Overview
A simple LTX-2.3 Video-to-Video workflow.
You can choose the reference from the original video using Depth, Canny, or OpenPose (default).
An inpaint Edit Mode has been added. You can "add," "delete," and "replace" elements using prompts (it's not universally applicable).
How to Use
• Motion Track Mode
Set Enable Motion Track Mode to yes and disable bypass.
Set Edit Mode to false.
Load the start image you want to animate.
Load the source video for tracing.
Specify a simple prompt (examples: comic style, dancing).
• Inpaint Edit Mode
Set Enable Motion Track Mode to no and enable bypass (not strictly required, but otherwise unnecessary processing will occur).
Set Edit Mode to true.
Load the video you want to edit.
Specify the edit in the prompt.
[Add]
Add a/an [subject/object] with [clear visual attributes], [precise location in the scene].
[Remove]
Remove the [subject/object] [location or identifying description].
[Replace]
Replace the [original subject/object] [location] with a/an [new subject/object] with [clear visual attributes].
[Convert / Style]
Convert the video into a [style name] style.
Description
Optimized to work with the latest version of ComfyUI (v0.18.1 + Frontend 1.42.8).
FAQ
Comments (5)
Returns an error - 1 ERROR
AttributeError: 'function' object has no attribute 'to'
When I downgrade the version, he writes
LTX2_NAG
'function' object has no attribute 'to'
First, try bypassing LTX2 NAG inside the LTX-2.3 Subgraph and check if it works.
Also, make sure that ComfyUI-KJNodes is updated to the latest version.
Thank you. The scheme is working. But I want to remake the video in a comic book style. And the video output is unchanged. https://imgbox.com/ijsrvFDP
@egus903841957 Thank you for the detailed report. I tested with comic-style images and tried several adjustments, but as you mentioned, partial realism seems to be added unintentionally.
It’s possible that LTX-2.3 V2V may not handle comic-style generation properly.
I’m sorry, but I’m unable to resolve this issue at the moment.
If you’d like, my Wan 2.2 Animate workflow also supports V2V. Please feel free to give it a try.
@egus903841957 Thanks for waiting. I’ve fixed it so you can now switch to comic style. Please give it a try.