ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

comfyui-video

Automate AI video generation with ComfyUI and LTX-2.3. Supports text-to-video (T2V), image-to-video (I2V), batch scene rendering for music videos, and multi-scene workflows. Includes progress monitoring, fault recovery, and performance tuning. Use when generating AI videos with ComfyUI, creating MV scenes in batch, troubleshooting video rendering, or optimizing generation speed.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/a3165458/comfyui-video
Or

ComfyUI Video Generation

Automate AI video generation using ComfyUI + LTX-2.3 model. Ideal for music video (MV) production, multi-scene batch rendering, and AI video content creation.

Requirements

ItemSpec
GPU≥24GB VRAM (Turing/Ampere/Ada)
ComfyUI0.17+
PyTorch2.6+cu124
AccessSSH tunnel forwarding port 18188

Model Setup

ModelSizePath
LTX-2.3 dev (bf16)43GBmodels/checkpoints/ltx-2.3-22b-dev.safetensors
Gemma 3 12B23GBmodels/text_encoders/comfy_gemma_3_12B_it.safetensors
Distilled LoRA7.1GBmodels/loras/ltxv/ltx2/ltx-2.3-22b-distilled-lora-384.safetensors
Video VAE (bf16)-models/vae/LTX23_video_vae_bf16.safetensors

Turing GPUs (e.g., Quadro RTX 8000) do NOT support fp8_e4m3fn. Use bf16/fp16 models only.

Performance Baseline

Per-step time: ~221s (constant, regardless of frame count!)
15 steps: ~57 min
25 steps: ~1h45m
Frames: 72=3s, 121=5s, 480=20s (24fps)

Key insight: Frame count does NOT affect total time. Bottleneck is model forward pass.

Workflow Node Reference

NodeIDPurpose
LoadImage2004I2V reference input
CLIPTextEncode (positive)2483Positive prompt
CLIPTextEncode (negative)2612Negative prompt
EmptyLTXVLatentVideo3059Empty latent
LTXVScheduler4966Steps/length params
LoraLoaderModelOnly4922+LoRA loader
SaveVideo4823/4852Output mp4

Quick Start

Generate a Single Video (I2V)

  1. Load workflow: /workspace/ComfyUI/custom_nodes/ComfyUI-LTXVideo/example_workflows/2.3/LTX-2.3_T2V_I2V_Single_Stage_Distilled_Full.json
  2. Set params using scripts/batch_scenes.js
  3. Click Run
  4. Wait ~1 hour
  5. Download from /workspace/ComfyUI/output/

Batch Scene Generation

Use scripts/batch_scenes.js for automation:

// Load script first, then configure each scene:
await comfyui_batch.configureScene({
  name: "scene_01",
  prompt: "A lonely girl running through rain at night, neon reflections",
  image: "unified_ref.png",
  steps: 15,
  frames: 72
});
// Click Run, repeat for next scene

Step Count Guide

StepsQualityTime/SceneUse Case
8Rough~30minQuick preview
15Good~57minRecommended sweet spot
25Best~1h45mFinal quality output

I2V + LoRA at 15 steps achieves ~90% of 25-step quality with 40% less time.

Troubleshooting

VAEDecode Validation Failed

Error: Exception when validating node: 'VAEDecode' Cause: VAE load timing or insufficient VRAM Fix: Reload the entire workflow (fetch + loadGraphData), wait for models to fully load, then run. Never reload during execution.

Browser Tab Lost

Metadata

Author@a3165458
Stars4473
Views0
Updated2026-05-01
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-a3165458-comfyui-video": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.