LTX-2.3 Long Video Generation (Distilled GGUF) workflows

Important Notice

Optimized to work with the latest version of ComfyUI (v0.18.1 + Frontend 1.42.8).

The latent upscaler ltx-2.3-spatial-upscaler-x2-1.1 has been released.
Version 1.0 had an issue where a strange overlay appeared at the end when generating long videos (241F+), but this has been fixed in 1.1.
Updating is strongly recommended.

Overview

A simple LTX-2.3 workflow. It uses the Distilled GGUF model for fast generation.

Latest News (v1.4)

Major feature update! An experimental extension feature has been added. You can extend videos by looping a specified length and number of iterations. Prompts can be defined for each chunk, enabling scenario-based generation.

Added a Double-Frame Mode. For use with intense motion. By rendering at twice the frame rate, facial distortion is less likely to occur.

Core Features

Single / Extend Generation Mode

You can choose whether to generate the video once or extend it afterward.

Three prompt input modes

1. Prompt enhancement using Ollama

2. Native LTX prompt enhancement

3. Plain (no enhancement)

If Ollama is not needed, you can disconnect it from the Ollama SubGraph node or simply delete the node.

1-pass / 2-pass selection

• 1-pass: Generates at the specified resolution (e.g., 1280×736).

• 2-pass: Recommended by Comfy / LTX. Generates at half resolution and then performs 2× upscaling.

Optional Features

Preview Switch: Displays a preview during sampling.

Audio-driven: Generates a video that matches an existing audio file.

T2V Switch: Ignores the start image and generates the video using text-to-video.

Full Mode: Generated using Steps 15 and CFG 3.0. This takes a very long time. While the camera work and motion may be slightly improved, the generation time is not practical.

Note

If you encounter the error, please update ComfyUI-KJNodes to the latest version.

For HD generation in 2-pass mode, please use 1280×768 or 768×1280.
If the shorter side is 734, it will be truncated to 704.