Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
Provide a clean, educational reference implementation for LTX 2.3 Text-to-Video generation.
Runtime profile
Source description
Workflow Goal
Provide a clean, educational reference implementation for LTX 2.3 Text-to-Video generation.
This workflow focuses on simplicity, reproducibility, and education rather than including every available feature. It provides a tested baseline for generating high-quality cinematic videos directly from text prompts while remaining easy to understand, modify, and extend.
Treat this workflow as a starting point and customize the prompt, and generation settings for your preferred artistic direction.
Version 1.0
Purpose
✓ Educational Reference Workflow
Sources
1 sourceSource excerpts
1 excerptSource context: 138 downloads · Type Workflows · Base model LTXV 2.3
✓ Clean Baseline Implementation
Features
✓ Wireless Modular Architecture
✓ Clean Reference Implementation
✓ Prompt Engineering Ready
✓ Two-Phase Sampling Pipeline
✓ Low VRAM Friendly
✓ Easy to Extend
Workflow Pipeline
Engine Configuration
↓
Video Clip Configuration
↓
Prompt Engineering
↓
Phase 1 Sampling (Audio & Video)
(Generate motion at the base latent resolution.)
↓
2x Spatial Upscale
(Increase latent spatial resolution.)
↓
Phase 2 Sampling (Audio & Video)
(Recover fine spatial details after upscaling.)
↓
VAE Decode (Audio & Video)
↓
Final Video Output
Verified Settings
The following settings were used to validate this workflow and are recommended as the baseline configuration.
Sampling
✓ CFG : 1.0
✓ Steps : 11 (8 + 3)
✓ Sampler : Euler Ancestral
Video
✓ Frames : 145 (6 seconds @ 24 fps)
✓ Output FPS : 24 FPS
✓ Tested Resolution : 1024 × 576 (16:9)
Required LoRA Configuration
I have not used any specific lora in this test workflow
Hardware & Resolution Notes
Validated using:
Hardware:
RTX 2080 8 GB
64 GB RAM
Resolution:
1024 × 576
Length:
6 seconds
Generation Time:
~12–13 minutes
Although compatible with 8 GB VRAM, LTX 2.3 Text-to-Video remains computationally intensive and memory hungry.
System RAM is equally important for handling intermediate tensors and memory paging during video generation.
Expected behavior:
8 GB VRAM + 16 GB RAM
Possible out-of-memory errors
Slower generation
8 GB VRAM + 32 GB RAM
Better stability
Performance depends on available system memory
8 GB VRAM + 64 GB RAM (or more)
Recommended configuration
If your system have better GPUs, use 720p or higher resolutions
Design Philosophy
This workflow intentionally avoids unnecessary complexity.
The objective is to provide a stable, reproducible reference implementation that users can understand, learn from, and extend for their own creative projects.
I haven't added sage attention or other optimizations deliberately in this workflow.
Requirements
Text encoder · 8.80 GB · SAFETENSORS · bf16 · Unknown
ltx-2.3_text_projection_bf16.safetensors
Not resolvedText encoder · Unknown
Upscaler · 950 MB · SAFETENSORS · bf16 · Unknown
VAE · 348 MB · SAFETENSORS · bf16 · full · Unknown
LTX23_video_vae_bf16.safetensors
File unverifiedVAE · Unknown · LTX23 Video VAE Bf16.safetensors
Checkpoint · 21.2 GB · Civitai · 2484503
cg-use-everywhere
FoundNode pack · Registry
comfyui-gguf
PossibleNode pack · Registry
Node pack · Registry
comfyui-mixlab-nodes
PossibleNode pack · Registry
comfyui-nhknodes
FoundNode pack · Registry
