A ComfyUI node acting as a mini video editor that combines text-to-video, image-to-video, first/last frame and custom audio workflows and stitches multiple clips. Designed for LTX 2.3 but works with LTX 2.5.

LTX Director
ComfyUI custom node that works as a timeline video editor for LTX video generation, with keyframes, audio and IC-LoRA support.
Updated EU status checked Last shown
LTX Director at a glance
- What is LTX Director?
- LTX Director is a library from WhatDreamsCost. ComfyUI custom node that works as a timeline video editor for LTX video generation, with keyframes, audio and IC-LoRA support.
- Who makes LTX Director?
- LTX Director is made by WhatDreamsCost.
- Does LTX Director work in the EU?
- Available in the EU. GPL-3.0 open-source code that can be downloaded and run locally anywhere, with no regional restrictions in the license or README. The underlying LTX models' own licenses are separate. Last verified 14 Nov 2026.
- How much does LTX Director cost?
- Open source, open source. Free to use; the author accepts optional donations via Ko-fi. Requires ComfyUI and LTX models run locally. Licence: GPL-3.0.
- Where was LTX Director shown?
- In 1 creator video by AI Search. Most recently by AI Search on 18 Aug 2026, at 15:32 in “The FASTEST local AI video generator”.
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
LTX Director is a custom ComfyUI node by WhatDreamsCost, distributed in the WhatDreamsCost-ComfyUI repository. It provides a timeline editor inside a node for working with LTX video models. It combines text-to-video, image-to-video, first/last-frame and custom-audio workflows, and can stitch multiple clips together. It succeeds the author's earlier LTX Sequencer and Multi Image Loader nodes. Creators describe it as designed for LTX 2.3 and also working with LTX 2.5.
Version 2.0 added video support (extending, trimming, splitting and combining clips on the timeline), IC-LoRA tracks, audio inpainting that blends imported and generated audio, a beta Retake mode for regenerating a segment of a shot, and saving/loading timelines as JSON. Version 2.0.4 added reference-image support through the LTX Ingredients IC-LoRA, model caching and other speed optimizations, and improved SageAttention/Triton compatibility. The repository also contains Load Video and Load Audio UI nodes and other ComfyUI nodes and workflows.
It is installed by cloning the repository into ComfyUI's custom_nodes folder or through ComfyUI Manager. It requires up-to-date ComfyUI-LTXVideo and ComfyUI-KJNodes. It runs locally, so hardware requirements depend on the underlying LTX models.
- Timeline editor inside a single ComfyUI node
- Combines text-to-video, image-to-video, first/last frame and custom audio
- Video extension, trim, split and combine on the timeline
- IC-LoRA tracks, including LTX Ingredients reference images
- Audio inpainting and beta Retake mode
- Save/load timelines as JSON
As seen on YouTube
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Similar AI tools
Closest neighbours by meaning, not just by category.
ComfyUI-MiniMaxH3-Easy
Library · nkxx188
ComfyUI custom node suite that simplifies MiniMax H3 video and image generation in a single compact workflow.
LTX 2.5 Upscaler with MiniMax
App
Community ComfyUI workflow that generates video with MiniMax and upscales it using the LTX 2.5 spatial upscaler.
ComfyUI
App · Comfy Org
Node-based visual AI engine for running image, video, audio and 3D generation workflows locally, in the cloud or via API.
LTX 2.5
Model · Lightricks
Open-weights Lightricks video model with native audio, multi-shot generation, auto duration and up to 4K output.
ComfyUI-Spectrum-MiniMax-H3
Library
ComfyUI custom node that speeds up MiniMax H3 audio-video sampling by forecasting skipped transformer steps.
LTX Trainer
Library · Lightricks
Official Lightricks package for training and fine-tuning LTX-2 video models, including LoRAs for characters, effects and styles.