Skip to content
WorkflowListedExternal
Download

LTX 2 For Low & High V-RAM GGUF + T2V + I2V with Lip Sync Using Comfy UI (1080p, 4K Videos) #ltx — v1.1

improved sound generation

Sourcecivitai.com/models/2299899
TaskMultiCapabilitiesImage to image · UpscalingFamilyLTX-VideoVersionRelease 2608545 — LTXV 2 Raretutor v1.1.jsonEstimated VRAMNot yet characterizedUnratedgrade

Runtime profile

Access
External workflow
Status
Listed
Version
LTXV 2 Raretutor v1.1.json
Source
Civitai
Updated
Nov 3, 2026

What you need

Model files
13.7 GiB known subtotal

Remaining hardware or download-size estimates are not available yet.

Requirements

Models

11

Node packs

17

  • ComfyLiterals

    Found

    Node pack · Registry

  • comfymath

    Possible

    Node pack · Registry

  • comfyui-custom-scripts

    Found

    Node pack · Registry

  • comfyui-easy-use

    Found

    Node pack · Registry

  • ComfyUI-GGUF

    PossibleOptional

    Node pack · Registry

  • comfyui-impact-pack

    Found

    Node pack · Registry

  • comfyui-kjnodes

    Found

    Node pack · Registry

  • ComfyUI-MelBandRoFormer

    Found

    Node pack · Registry

  • comfyui-videohelpersuite

    Found

    Node pack · Registry

  • Fast Groups Bypasser (rgthree)

    Not resolved

    Node pack · Unknown

  • GetNode

    Not resolved

    Node pack · Unknown

  • Label (rgthree)

    Not resolved

    Node pack · Unknown

  • LowVRAMLatentUpscaleModelLoader

    Found

    Node pack · Unknown

  • LTXVSpatioTemporalTiledVAEDecode

    Not resolved

    Node pack · Unknown

  • monnky/ComfyUI-Monnky-LTXV2

    Not resolved

    Node pack · GitHub · monnky/ComfyUI-Monnky-LTXV2

  • rgthree-comfy

    Found

    Node pack · Registry

  • SetNode

    Not resolved

    Node pack · Unknown

AI-generated commentary

AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.

Purpose

  • This ComfyUI workflow creates video from a text prompt or image, with text-to-video, image-to-video, lip-sync, and LTXV-audio or custom-audio paths; its title advertises 1080p and 4K video.

Flow

  • The walkthrough loads an LTX Safetensor or GGUF model, then shows text-to-video and image-to-video examples, including LTXV Audio and custom audio.

Inputs and outputs

  • A text prompt or source image selects the video path; the walkthrough also names LTXV Audio and custom-audio variants, and the title names video and lip sync.

Setup

  • Before opening the workflow, the notes ask you to update or download ComfyUI-Monnky-LTXV2, ComfyUI-KJNodes, and ComfyUI-LTXVideo.

  • If MonnkySamplerLTXV is missing, the notes say it cannot be installed through the standard ComfyUI Manager search; remove prior ComfyUI-PainterLTXV installs, clone ComfyUI-Monnky-LTXV2 into ComfyUI/custom_nodes/, and restart ComfyUI.

Dependencies

  • The workflow lists these node dependencies: ComfyLiterals, comfymath, comfyui-custom-scripts, comfyui-easy-use, ComfyUI-GGUF, comfyui-impact-pack, comfyui-kjnodes, ComfyUI-MelBandRoFormer, and comfyui-videohelpersuite.

  • It also lists Fast Groups Bypasser (rgthree), GetNode, Label (rgthree), LowVRAMLatentUpscaleModelLoader, LTXVSpatioTemporalTiledVAEDecode, monnky/ComfyUI-Monnky-LTXV2, rgthree-comfy, and SetNode.

  • Listed model files are gemma_3_12B_it_fp8_e4m3fn.safetensors, ltx-2-19b-distilled_Q4_K_M.gguf, ltx-2-19b-distilled-fp8.safetensors, ltx-2-19b-distilled.safetensors, ltx-2-19b-ic-lora-detailer.safetensors, ltx-2-19b-lora-camera-control-dolly-left.safetensors, ltx-2-spatial-upsc in

Configuration

  • In the walkthrough, LTXV Audio paths and text-to-video with custom audio use an FP8 distilled model; image-to-video with custom audio uses a Q4 GGUF model.

  • Embedded size notes pair Low VRAM 640 x 360 with 1280 x 720 (720p HD), Mid VRAM 960 x 512 with 1080 x 1024 (Full HD), High VRAM 1280 x 704 with 2560 x 1408 (2K), and Very High VRAM 1920 x 1024 with 3840 x 2048 (4K).

  • Version 1.1 notes audio normalization as a change to sound generation.

Cautions

  • The listing does not specify a license for using the model.

Does this need to be edited?

Sign in to send an edit request.

Sources

1 source
CivitaiPrimaryVersion 2608545
civitai.com/models/2299899

Verified Nov 3

Workflow instructions

Author notes from LTXV 2 Raretutor v1.1.json · selected release

Low Vram : 640 x 360 -> Final Video after Upscale : 1280 x 720 (720p HD) Mid Vram : 960 x 512 -> Final Video after Upscale : 1080 x 1024 (Full HD) High Vram : 1280 x 704 -> Final Video after Upscale : 2560 x 1408 (2K) V. High Vram : 1920 x 1024 -> Final Video after Upscale : 3840 x 2048 (4K)

Author notes from LTXV 2 Raretutor v1.1.json · selected release

[Click here to Download Models](https://www.youtube.com/watch?v=caOcU-k9_A4 )

Author notes from LTXV 2 Raretutor v1.1.json · selected release

16/01/2026 After LTX team updated Distilled fp8 model, not sure about VAE. Please test with loading individual Video and Audio VAE. use which best works for you.

Download files

Model artifacts

2 artifacts

ltx2ForLowHighVRAMGGUFT2VI2VWith_v11.zip

zip · 19.8 KB · SHA-256 13b4605f4dcb…4a4d · Civitai

Download file

LTXV 2 Raretutor v1.1.json

json · 176 KB · SHA-256 20d81aaec6ec…bdbc

Download file

Source excerpts

3 excerpts
NoteNov 3civitai.com/models/2299899

Source context: 2676 downloads · Type Workflows · Base model LTXV

NoteOct 2civitai.com/models/2299899

Source context: 2631 downloads · Type Workflows · Base model LTXV

NoteJul 18civitai.com/models/2299899

Source context: 2470 downloads · Type Workflows · Base model LTXV