LTX23-Ultimate

A simple, color-coded GGUF workflow for running LTXV-2.3 in ComfyUI. Designed to be straightforward and lightweight.

Required Node Packs

ComfyUI-GGUF https://github.com/city96/ComfyUI-GGUF

ComfyUI-KJNodes https://github.com/kijai/ComfyUI-KJNodes (install & update it to nightly)

ComfyUi-Jakeupgrade https://github.com/jakechai/ComfyUI-JakeUpgrade

Comfyui-VHS https://github.com/kosinkadink/ComfyUI-VideoHelperSuite

additional install via manager

https://huggingface.co/Kijai/LTX2.3_comfy/tree/main

Includes:

Distilled LoRA (REQUIRED)

Text Projection (embedding connector)

https://huggingface.co/unsloth/LTX-2.3-GGUF/tree/main

Includes:

Diffusion Models (GGUF)

VAE

Choose based on VRAM:

Q4_K_M → lower VRAM (recommended)

Q8_0 → higher quality, more VRAM

⚠️ Very low quants = basically unusable ✍️ Text Encoders (REQUIRED)

https://huggingface.co/Comfy-Org/ltx-2/tree/main/split_files/text_encoders

Gemma text encoder

➡️ You still ALSO need:

Text Projection (from Kijai’s repo)

🔍 Latent Upscaler

https://huggingface.co/Lightricks/LTX-2/tree/main/

Files:

ltx-2-spatial-upscaler-x2-1.0.safetensors

ltx-2-temporal-upscaler-x2-1.0.safetensors

⚠️ Important Notes

Use DEV GGUF diffusion models but distilled are possible

Distilled LoRA is still REQUIRED

Most issues = outdated nodes or ComfyUI

.