LtxMTV is a APP MODE 2-Minutes Music Video Generator
Runtime profile
Source description
LtxMTV is a APP MODE 2-Minutes Music Video Generator
(for best results use 50FPS and be patient :) )
using Ace1.5 / 4b and Ltx2.3 Distilled FP8
both downloadable directly from Comfyui.
It's using KJNodes as Custom Nodes.
Options:
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
LtxMTV generates a two-minute music video from two images, lyrics, musical style, language, BPM, FPS, and time signature, producing six 20-second scenes that alternate the images as start frames.
The workflow offers an app mode and a Work Flow mode with more options.
Enter lyrics and choose a musical or singer style, language, BPM, FPS, and time signature.
Choose two images; they alternate as start frames across the six-scene video.
This is version v1.0 from WanApp, based on LTXV 2.3; no license is specified.
Ace1.5 / 4b and LTX 2.3 Distilled FP8 are listed as downloadable directly from ComfyUI.
The workflow lists the ComfyUI-KJNodes node pack, identified as comfyui-kjnodes.
Listed model files include ace_1.5_vae.safetensors, acestep_v1.5_turbo.safetensors, qwen_0.6b_ace15.safetensors, and qwen_4b_ace15.safetensors.
Other listed files are ltx-2.3-22b-dev-fp8.safetensors, gemma_3_12B_it_fp4_mixed.safetensors, ltx-2.3-spatial-upscaler-x2-1.1.safetensors, and ltx-2.3-22b-distilled-lora-384.safetensors.
Automatic image resizing can target 480p or 544p.
The workflow suggests 50 FPS and indicates that Work Flow mode has more options.
Suggestion · not verified
Before use, verify that qwen_4b_ace15.safetensors, qwen_0.6b_ace15.safetensors, acestep_v1.5_turbo.safetensors, and ace_1.5_vae.safetensors are available in your ComfyUI setup.
Suggestion · not verified
Also verify that ltx-2.3-22b-distilled-lora-384.safetensors is available before use.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
3 excerptsSource context: 310 downloads · Type Workflows · Base model LTXV 2.3
Auto-Image Resize to 480p or 544p
FPS
BPM
Lyrics
Musical Style
Language
Time Signature
Write your lyrics, pick your music/singer style
Choose 2 Images, Each scene duration is 20 seconds for a total 6 scenes with alternating between those 2 images as a start frame.
Making a good quality music video with minimal effort.
for more options, go in Work Flow mode.
Tested on a 14900k / nvidia 5080 with 64go Ram
Remaining hardware or download-size estimates are not available yet.
Requirements
VAE · Hugging Face · Comfy-Org/ace_step_1.5_ComfyUI_files · aceStepAudioGen_vae.safetensors
acestep_v1.5_turbo.safetensors
File unverifiedCheckpoint · Hugging Face · Comfy-Org/ace_step_1.5_ComfyUI_files · acestepV15Turbo_v15.safetensors
Source context: 292 downloads · Type Workflows · Base model LTXV 2.3
Source context: 254 downloads · Type Workflows · Base model LTXV 2.3
gemma_3_12B_it_fp4_mixed.safetensors
File unverifiedText encoder · Hugging Face · Comfy-Org/ltx-2 · Ltx 2
ltx-2.3-22b-dev-fp8.safetensors
File unverifiedVAE · Hugging Face · Lightricks/LTX-2.3-fp8 · LTX 2.3 FP8
LoRA · 7.08 GB · Hugging Face · Lightricks/LTX-2.3
ltx-2.3-spatial-upscaler-x2-1.1.safetensors
File unverifiedUpscaler · Hugging Face · Lightricks/LTX-2.3 · LTX 2.3
Text encoder · Hugging Face · Comfy-Org/ace_step_1.5_ComfyUI_files · ACE-Step Audio Gen (TEnc qwen_0.6b_ace15)
Text encoder · Hugging Face · Comfy-Org/ace_step_1.5_ComfyUI_files
Node pack · Registry