Aitrepreneur
patreon
LTX-2 THE NEW IMAGE TO VIDEO WITH SOUND AI KING WITH LOWVRAM!
🕑 Added 2026-01-17 19:57:49 +0000 UTCHey everyone! I've created a 1-click installer for the new IMAGE TO VIDEO WITH SOUND KING, called “LTX-2”. It’s an absolutely insane open source model that can generates videos with sound from either a simple text prompt, an image or even a sound file and can run on LESS THAN 8GB OF VRAM! This is one of the most fun model I have ever tried!
You can check out the video right here: https://youtu.be/KKdEgpA3rjw
The workflow: https://www.patreon.com/posts/148469815
The installer of course automates the entire install process for comfyUI and the models downloads!
LOCAL INSTALL!!! RECOMMENDED TO START FROM SCRATCH
Download the LTX-2-ULTRA-COMFYUI-MANAGER_AUTO_INSTALL.bat
Run the bat file
Wait for the install to finish
The webui will launch, load the LTX-2_ULTRA_WORKFLOW.json file and there you go😎
DON'T FORGET TO GO UPDATE COMFYUI BY GOING INSIDE THE UPDATE FOLDER AND RUNNING THE COMFYUI UPDATE BAT FILE THEN CHOOSING THE CORRECT LAUNCHER FOR YOUR GPU!!
IF YOU ALREADY HAVE COMFYUI INSTALLED USING A PREVIOUS INSTALLER:
Download the LTX-2-MODELS-NODES_INSTALL.bat and place it in the ComfyUI_windows_portable\ComfyUI folder
Run the bat file
Wait for the install to finish
???
Profit 😎
IF YOU GET AN ERROR WHEN LAUNCHING COMFYUI AFTER USING THIS INSTALLER SAYING "AssertionError: Torch not compiled with CUDA enabled" it's ok don't panic.
Just go inside the python embedded folder, click on the folder path, type cmd press enter, this will bring the command prompt window and there type:
python.exe -m pip uninstall torch
python.exe -s -m pip install --upgrade torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128
--->replace cu128 by your cuda version (if you don't know your cuda version just open a new cmd window and type nvcc --version it will then tell you at the end Cuda compilation tools, release 12.8, V12.8.93 or something different like 12.6, in that case just use cu126 instead of cu128)
IF YOU ARE USING RUNPOD:
Create an account if you haven't already: Runpod
Click on Pod (on the left side) then click deploy
Choose a GPU with at least 24gb of VRAM (4090 is best), click here for the comfyui template (aitrepreneur/comfyui), then edit the template and choose 100gb for both the container and volume disk, then deploy on demand
Go to my pods, wait for everything to finish and then click "connect", then "Connect to HTTP SERVICE port 3000" and click on the manager to update comfyui and restart it
Then go to the port 8888, go inside the comfyui folder and then drag and drop the LTX-2-AUTO_INSTALL-RUNPOD.sh file on the left side of the UI then click on the "Terminal" icon on the right side on the UI
Copy and paste these two lines then press enter:
chmod +x LTX-2-AUTO_INSTALL-RUNPOD.sh
./LTX-2-AUTO_INSTALL-RUNPOD.sh
Wait for everything to be installed
Go back to the port 3000 and click on the manager and restart it
Load the LTX-2_ULTRA_WORKFLOW.json file and there you go😎
Also use the command:
tail -f comfyui.log
inside the workspace/logs to get the real time logs so that you always know when the install is done. It will then ask you to restart, so click on that restart button, wait for the webui to reboot, click refresh once it's done and there you go.
IF YOU GET OOM error :
Click on the little 3 dots button, arguments variables then enter
EXTRA_ARGS --reserve-vram 10 --cache-none
then restart the pod
As always, supporting me on Patreon allows me to keep creating helpful resources like this for the community. Thank you for your support - now go have some fun😉!
Comments
Andres Posada
would be much appreciated if updated to LTX 2.3...thx
--------
love it. Any chance of a LTX 2.3 update?
CenturionEd
anyone getting this error: ValueError: cannot reshape array of size 11071770 into shape (4096,4352)
Ken Kawashima
Now waiting for a workflow update for the new LTX 2.3 22B Dev. The current workflow is utterly incompatible, requiring new models and ComfyUI nodes.
Keen
Tried using this command... but maybe I am not putting it in the right place? "Install PIP packages" did not like this command: pip install --upgrade imageio-ffmpeg And did not like imageio-ffmpeg by itself either.
Keen
So looks like all the rendering worked while I was eating dinner... and then a new error popped up. VHS_VideoCombine ffmpeg is required for video outputs and could not be found. In order to use video outputs, you must either: - Install imageio-ffmpeg with pip, - Place a ffmpeg executable in P:\AI_Downloads\ComfyUI_windows_portable, or - Install ffmpeg and add it to the system path. Show Report Help Fix This ---------More detail----------- # ComfyUI Error Report ## Error Details - **Node ID:** 514 - **Node Type:** VHS_VideoCombine - **Exception Type:** ProcessLookupError - **Exception Message:** ffmpeg is required for video outputs and could not be found. In order to use video outputs, you must either: - Install imageio-ffmpeg with pip, - Place a ffmpeg executable in P:\AI_Downloads\ComfyUI_windows_portable, or - Install ffmpeg and add it to the system path.
Keen
I found MelBandRoformer_fp32.safetensors on https://huggingface.co/Aitrepreneur/FLX/tree/main and I have placed that file in the loras subfolder under models in ComfyUI. Let me know if you think that is a bad idea, lol. Also, that directory is great -- thanks to another user who posted it in these Patreon chats. I found unet files there that I also did not have for Klein and LTX-2. Ran the run file again (tried all three of them, just in case), and unfortunately the safetensors file did not address the missing nodes -- same error: This workflow uses custom nodes you haven't installed yet. MelBandRoFormerModelLoader Switch any [Crystools] in subgraph 'New Subgraph' MelBandRoFormerSampler in subgraph 'New Subgraph' Install these nodes to run this workflow, or replace them with installed alternatives. Missing nodes are highlighted in red on the canvas.
Keen
So it looks like my problem is with nodes. :) I have tried downloading lots of safetensors from the huggingface site (see the reply below). But honestly, I am just guessing where to place these files. :) Would appreciate a nudge in right direction. Am going to see if the manual installation guide helps. This workflow has missing nodes This workflow uses custom nodes you haven't installed yet. MelBandRoFormerModelLoader Switch any [Crystools] in subgraph 'New Subgraph' MelBandRoFormerSampler in subgraph 'New Subgraph' Install these nodes to run this workflow, or replace them with installed alternatives. Missing nodes are highlighted in red on the canvas.
Lucas Quinteiro Valenzuela
why it says that has missing nodes? i followed all the steps for the 1click installer. Installation Required Install Required Sam2Segmentation Install Required DownloadAndLoadSAM2Model Install Required WanVideoTextEncodeCached Install Required WanVideoSampler Install Required WanVideoClipVisionEncode Install Required WanVideoVAELoader Install Required WanVideoBlockSwap Install Required WanVideoDecode Install Required SeCModelLoader Install Required SeCVideoSegmentation Install Required WanVideoAnimateEmbeds Install Required WanVideoSetLoRAs Install Required WanVideoSetBlockSwap Install Required WanVideoTorchCompileSettings Install Required WanVideoModelLoader Install Required OnnxDetectionModelLoader Install Required PoseAndFaceDetection Install Required WanVideoLoraSelectMulti Install Required DrawViTPose
Complex Avocado
I need my subscription canceled please help. Ive resubscribed on a new account and i’d like to keep subscribing however, i lost my access to my old account 2 months ago, I cant find another way to reach out to you personally. Previous account was Hannaali**995@gmail.com card ending in 3083
Lukas Félix
Will the model and workflow work in an AMD setup? I'm trying to get it working but I keep getting the error: LTXVImgToVideoInplace cannot unpack non-iterable NoneType object
Robert Morton
Will this work with the comfyui AMD version ? it uses pytorch compiled for rocm7.2
Aitrepreneur
Yep just came back from vacations and bam! Z image base is here, I've been testing it since it came out. I'm not done testing it yet once I'm done the video will be out
John
I have this workflow running really well. The only issue I have is the I2V entirely ignores the source image. Characters, background, lighting, everything. It seems like it's only pulling from the text prompt and not the image. Anyone else having this issue? I'm sure it's something stupid I'm missing. I've used Grok to write my prompts also.
John Juarez
Hey man! Loving LTX-2! Z-image base workflow and vid soon? You da man :)
Eyes_Wide_Shut
I knew you would come through 🙏👏
Andrius
its possible to make continue video like on wan2gp? Then can make basically infinity long...
kaczorefx
Overlord - the link to the 16gb launcher bat is invalid in the installer
kaczorefx
Ok, got it. should be " .\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build --cache-none --reserve-vram 7 echo If you see this and ComfyUI did not start try updating your Nvidia Drivers to the latest. If you get a c10.dll error you need to install vc redist that you can find: https://aka.ms/vc14/vc_redist.x64.exe pause "
kaczorefx
Can someone post the "run_nvidia_gpu-LTX2-16GB+.bat" file? It keeps creating it with "No Entry Found" text inside and doesn't work. Two other files are created correctly :o
