-
Notifications
You must be signed in to change notification settings - Fork 258
Description
In the 2025 version, the LTXV In Context Sampler had an optional_cond_image, you could provide it an image and it would work as the first frame.
ComfyUI-LTXVideo/easy_samplers.py
Lines 487 to 492 in ee11be3
| "optional_cond_image": ( | |
| "IMAGE", | |
| { | |
| "tooltip": "The image to use for conditioning the sampling, if not provided, the sampling will be unconditioned (t2v setup). The image will be resized to the size of the first frame." | |
| }, | |
| ), |
But in the latest version 2026, it has been replaced with optional_cond_images
ComfyUI-LTXVideo/easy_samplers.py
Lines 649 to 654 in e1d2cff
| "optional_cond_images": ( | |
| "IMAGE", | |
| { | |
| "tooltip": "The image to use for conditioning the sampling, if not provided, the sampling will be unconditioned (t2v setup). The image will be resized to the size of the first frame." | |
| }, | |
| ), |
And now it no longer works.
If I provide it a single image, I now get error 'NoneType' object is not iterable
If I provide it video images, I also get the error 'NoneType' object is not iterable
Normally you would give it an image, but since it was renamed to images, then maybe it now wants images. But I don't think so. I think it wants an image, despite the renaming of it. But it no longer accepts an image.