[edit:
24.04.2026: Update version 4.3 (see version description).
Minor update and bug fix.
Thanks to all users for the many inputs over the last days and weeks 馃檪
Attention:
If you struggle with node conflicts or you get errors while running the workflow, please have a look at my short Trouble Shooting Guide note in the wokflow first. Most importent is to update all components sucsessfully! ]
Special thanks to:
@ArcleinSK for investigation and solving the FLF issue, as well as forcing the First-Mid-Last Frame option and last but not least for charing fantastic knowlage.
@boinobin730 for initialising, forcing and supporting this project in all kinds of matter, like providing links, running tests, sharing knowlage and inspiring diskussions.
@Urabewe for publishing the original, perfectly running 12 GB VRAM LTX-2.3 workflows mainly used here in this workflow.
Features:
Simple to use all-In-One LTX-2 workflow with options for:
Text to Video
Image to Video
First/Last Frame to Video
Fisrt/Mid/Last Frame to Video
Video to Video
Text + Audio to Video
Image + Audio to Video
First/Last Frame + Audio to Video
First/Mid/Last Frame + Audio to Video
easy switching between all options,
all steps highly automated: no manual frame or width/hight calculations necessary,
easy to set inputs by predefined sliders and aspeckt ratio inputs (no risk to set wrong frame counts or wrong width/hight values),
completely automated resizing and cropping (if necessary) of your input images/videos.
brilliant audio generation (speech/sound) with LTX-2.3.
LTX-2.3 specifications:
Workflow version v4.3 consistently follows the LTX-2.3 specifications for 16:9/9:16 aspect ratios, including automatic width/hight calculations, as well as automatic input image/video resizing/cropping.
In addition you can simply choose now any other aspect ratios according to your needs while still getting the right values calculated for width/hight and automatic image/video resize/crop.
Requirements:
GPU with 12 GB VRAM (some users reported they got it running with 8 GB too),
32 GB VRAM,
Swap file size: 64 - 128 GB.
Speed and video length:
Runs very fast: 5 second (1280 x 864) Video: < 10 minutes.
Generation of long high quality videos in one run possible: 10 - 20 seconds without any issues,
Testrun: 30 second video (1024 x 704) tooks around 40 minutes without any OOM errors. Longer videos might be possible, but not tested yet.
Important:
This workflow is intended for advanced comfyui users who know how to install and operate the system and are able to resolve basic system errors themselves, like as node conflicts, or general system issues.
About this workflow:
This workflow is mainly based on the fantastic LTX-2.3 workflows of @Urabewe.
As far as I know, those were the first workflows running LTX-2 with 12 GB VRAM. All credits goes to the original creator.
My job was only to combine and organise the different workflows in a simple to use all-in-one design.
Description
Small bug fix
FAQ
Comments (16)
What's up with the safetensors in the extra_model_name field of the GGUF loader? It won't find the safetensors, and won't load embedding connector safetensor that's there by default.
I also thought so. Upgrade Comgy to 0.15 and front_end and nodes. Then this model will show up in the drop-down menu
@PopHorn1956聽Thank you for giving the hint to upgrade all components. With existing installations we often forget to update the nodes too.
I actually can`t remember who gave the hint - but set the extra_model_name to "None" finally. And to be honest, I really do not understand for myself why the new gguf loader works and the old one did not with latest comfyui updates 馃檮
a mess with folders and paths
agree: TypeError: expected str, bytes or os.PathLike object, not NoneType
This is the ONLY workflow I've been able to get to work (other than the template). It's so straightforward and just works. Thank you!! Do you by chance have an fp8 distilled version or know how easy it would be to modify?
Hi - thank you so much 馃構 Unfortunately I have never tried fp8 distilled models yet and I have no experiances with different LTX models. Do you have some more informations, like: will this work with 12 gb vram and low steps, example workflows and model sources? What would be the advantage of this model?
@arkinson聽no problem, I have a 3090 and am trying to use best quality possible For 24 GB with a simple and powerful workflow Like yours
@cleonthethird聽Ahh - ok, 24 gb vram is a completely different league, of course. Did you tried around to use the fp8 model?
@arkinson聽Yes the fp8 distilled is what I was using with the default workflow in comfy - Produced good results, but the workflow could be better :)
@cleonthethird I havn`t the recources for "larger" experiments yet, but I had a short look at the template workflow. It seems to be easy: Have a look into the subgraphs and just replace the models (evetually even the loaders), remove the "low step Lora" and use the sigmas/steps from the template. That is all no rocket science at least 馃槈
TypeError: expected str, bytes or os.PathLike object, not NoneType
@Cor4411 You obviously have issues with your comfyui system wich is common, especially after the latest major comfyui updates. Look at the comfyui guidlines for troubleshooting or just go the easy way and install a fresh system for video generation, like Comfyui-Easy-Install.
same error here. Its the wild west out there...
@arkinson聽I do use easy-install (updated) and it just won't work
@Cor4411聽Sorry, but without usefull informations I can`t help you.