Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
IF YOU ARE WONDERING WHAT V2 IS OR YOU'RE HERE BECAUSE OF MISMATCHES AFTER UPDATING COMFY THE FIX IS IN!
Runtime profile
Source description
IF YOU ARE WONDERING WHAT V2 IS OR YOU'RE HERE BECAUSE OF MISMATCHES AFTER UPDATING COMFY THE FIX IS IN!
UPDATE KJNODES AND COMFY!!!!!
WE NOW PUT THE EMBEDDINGS INTO THE MODEL LOADER AND THE CLIP BUT IT IS ONLY LOADED ONCE! DOES NOT USE MORE MEMORY!
UPDATE KJNODES AND COMFY!!!!!
THIS WAS A NECESSARY CHANGE AFTER COMFY REORGANIZED WHERE THE EMBEDDING MODEL WOULD LOAD INTO. REQUIRED UPDATE!
PLEASE TAKE NOTE OF NEW DEV+LORA COMBO! WE NOW USE FP4 GEMMA TEXT ENCODER!!!! CHECK MODELS!!! WE NOW HAVE PREVIEWS USING TINY VAE!!! CHECK MODELS!!!! CHECK MODELS!!! DID I MENTION TO CHECK ALL YOUR MODELS!!! DO EEEEEEET!
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
This ComfyUI workflow is for generating LTX-2 video from a text prompt, image, short video clip, or audio paired with text or an image; it supports text-to-video, image-to-video, video extension, text-plus-audio video, and image-plus-audio lip-sync, with video outputs.
The five described paths are t2v, i2v, v2v extend, ta2v, and ia2v.
Use v2v extend with a few seconds of video and a prompt to continue it; ta2v uses text and audio, while ia2v uses an image and audio.
Text-to-video uses a text prompt; image-to-video uses an image; video extension uses a few seconds of video and a prompt; audio paths use audio with text or an image.
The described outputs are generated videos, including audio-driven video and image-plus-audio lip-sync results.
The description lists at least 12 GB of VRAM and 48 GB of system RAM; compare those figures with your setup before use.
Suggestion · not verified
Named non-optional files include: gemma_3_12B_it_fp4_mixed.safetensors; ltx-2-19b-dev-Q4_K_M.gguf; ltx-2-19b-distilled-lora-384.safetensors; and ltx-2-19b-embeddings_connector_dev_bf16.safetensors.
Other named non-optional files are: ltx-2-spatial-upscaler-x2-1.0.safetensors; LTX2_audio_vae_bf16.safetensors; LTX2_video_vae_bf16.safetensors; and taeltx_2.safetensors.
The named node pack is comfyui-kjnodes.
The V2 notes instruct you to update KJNodes and Comfy and to load embeddings through the model loader and CLIP once.
The description calls out an FP4 Gemma text encoder, a dev-plus-LoRA combination, Tiny VAE previews, and two audio-enhancement nodes near the end.
Before setup, verify the intended source and version for ltx-2-19b-distilled-lora-384.safetensors and ltx-2-spatial-upscaler-x2-1.0.safetensors; no checksum is listed for ltx-2-19b-embeddings_connector_dev_bf16.safetensors, LTX2_video_vae_bf16.safetensors, or taeltx_2.safetensors
Suggestion · not verified
No license is specified on the source page; check the applicable terms before use.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
1 excerptSource context: 20067 downloads · Type Workflows · Base model LTXV2
WE ALSO HAVE THE LORAS SETUP CORRECTLY AND THERE ARE SOME FUN ONES OUT ALREADY! NODE IS READY TO GO FOR YOU!
5 TOTAL GGUF 12GB WORKFLOWS!
t2v, i2v, v2v extend, ta2v, ia2v!
Hello everyone! This workflow has come a long way since 1.0 actually. It doesn't seem like it when you first look but, boy this has been a project for me!
Here we have quite a few workflows for LTX-2 using GGUF and running on at least 12GB VRAM and 48GB system ram.
First we have your typical t2v and i2v workflows.
Second we now have two new audio driven workflows! ta2v which is supply a text prompt ONLY and some audio get a neat generated video with your audio! The other is an ia2v where you supply an image and an audio file and it lip-syncs up nicely. I tried to keep everything as simple as possible.
Then the one I like the most v2v extend. Feed ltx2 a few seconds of video, create a prompt to continue the video and watch the magic happen!!
I got done with the workflows, I now need to get all the info out there but I wanted to get these into the wild so everyone can start having fun with them!
I HAVE CREATED TWO ENHANCEMENT NODES FOR THE AUDIO!!
YOU WILL NOTICE 2 NEW NODES TOWARD THE END OF THE WORKFLOW FOR AUDIO ENHANCEMENT. CLICK THE BLUE LINK BELOW FOR MY GITHUB PAGE, INSTALLATION INSTRUCTIONS, AND USEAGE NOTES!
URABEWE-COMFYUI-AUDIOTOOLS
Estimated VRAM requirement
Estimate unavailable
20.0 GB across 3 of 8 model files. Model file total + 25% loading overhead + 2 GB execution buffer, rounded up.
Requirements
9 requirementsgemma_3_12B_it_fp4_mixed.safetensors
File unverifiedText encoder · Civitai · 2817877
Checkpoint · 12.0 GB · Hugging Face · unsloth/LTX-2-GGUF
LoRA · 7.15 GB · Hugging Face · Lightricks/LTX-2
ltx-2-19b-embeddings_connector_dev_bf16.safetensors
Not resolvedText encoder · Unknown
Upscaler · 950 MB · Hugging Face · Lightricks/LTX-2
LTX2_audio_vae_bf16.safetensors
File unverifiedVAE · Hugging Face · novoluz/ltx2_audio_vae_bf16 · Ltx2 Audio VAE BF16
LTX2_video_vae_bf16.safetensors
Not resolvedVAE · Unknown
taeltx_2.safetensors
Not resolvedVAE · Unknown
Node pack · Registry
