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
This workflow is based on LTX-2.3 I2V/FLFV and supports multi-frame processing. It allows you to visually specify image ordering and keyframe timing. Special thanks to WhatDreamsCost for providing the powerful custom nodes.
Core Features
Three prompt input modes
Prompt enhancement using Ollama
Native LTX prompt enhancement
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., 1280×768).
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.
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.
Description
3/29 : Minor fix
First Release
FAQ
Comments (7)
The idea looks great but I'm getting:
Failed to validate prompt for output 1316:
[2026-03-27 16:02:00.111] [error] * CFGGuider 167:1528:154:
- Required input is missing: positive
- Required input is missing: model
- Required input is missing: negative
* MultimodalGuider 167:1524:1520:
- Required input is missing: positive
- Required input is missing: model
- Required input is missing: negative
* BasicScheduler 167:1528:1472:
- Required input is missing: model
* BasicScheduler 167:1524:1541:
- Required input is missing: model
I have the same bullshit.
Failed to validate prompt for output 1316:
* BasicScheduler 167:1524:1541:
- Required input is missing: model
* BasicScheduler 167:1528:1472:
- Required input is missing: model
* TrimAudioDuration 1485:
- Required input is missing: audio
* MultimodalGuider 167:1524:1520:
- Required input is missing: model
- Required input is missing: positive
- Required input is missing: negative
* CFGGuider 167:1528:154:
- Required input is missing: model
- Required input is missing: positive
- Required input is missing: negative
Output will be ignored
HTTP Request: POST http://127.0.0.1:11434/api/generate "HTTP/1.1 200 OK"
Prompt executed in 6.01 seconds
I’m unable to replicate the error on my PC. For reference, here is my ComfyUI environment:
Windows 11, Nvidia RTX 3090
Python 3.12.9 (tags/v3.12.9:fdb8142, Feb 4 2025, 15:27:58) [MSC v.1942 64 bit (AMD64)]
PyTorch 2.10.0+cu130
ComfyUI 0.18.1, ComfyUI_frontend 1.39.19, Node2.0 disabled, Ollama
Arguments:
main.py --front-end-version Comfy-Org/[email protected] --disable-smart-memory --auto-launch --preview-method auto --enable-manager --enable-manager-legacy-ui --user-directory F:\Documents\ComfyUI\user --output-directory F:\Documents\ComfyUI\output
@javawock7618 Maybe it would be easier for you to upload an image of the completed workflow so I could copy it? Rather than go through the hassle of trying to figure out the cause. I'm not the only one experiencing this error.
@bionovafood863 You can download the example video and verify the workflow used when it was functioning correctly. I have also uploaded a screenshot on my end.
@javawock7618 I tried again, still the same error. Sad.
Failed to validate prompt for output 1316:
* BasicScheduler 167:1524:1541:
- Required input is missing: model
* BasicScheduler 167:1528:1472:
- Required input is missing: model
* MultimodalGuider 167:1524:1520:
- Required input is missing: negative
- Required input is missing: model
- Required input is missing: positive
* CFGGuider 167:1528:154:
- Required input is missing: negative
- Required input is missing: model
- Required input is missing: positive
Output will be ignored
Prompt executed in 0.06 seconds
got prompt
Failed to validate prompt for output 1316:
* BasicScheduler 167:1524:1541:
- Required input is missing: model
* BasicScheduler 167:1528:1472:
- Required input is missing: model
* MultimodalGuider 167:1524:1520:
- Required input is missing: negative
- Required input is missing: model
- Required input is missing: positive
* CFGGuider 167:1528:154:
- Required input is missing: negative
- Required input is missing: model
- Required input is missing: positive