RuneXX/LTX-2.3-Workflows
Summary
This Hugging Face repository provides workflows and model downloads for Lightricks' LTX-2.3 video generation model, designed for use with ComfyUI, including split models, GGUF versions, and required custom nodes.
View Cached Full Text
Cached at: 05/13/26, 06:11 PM
RuneXX/LTX-2.3-Workflows · Hugging Face
Source: https://huggingface.co/RuneXX/LTX-2.3-Workflows Your browser does not support the video tag.The workflows are based on the extracted models fromhttps://huggingface.co/Kijai/LTX2.3_comfyThe extracted models might run easier on your computer (as separate files). (but you can easily swap out the model loader for the ComfyUI default model loader if you want to load the checkpoint with “all in one” vae built-in etc)
LTX-2.3 Main Model Downloads (split models):
- Main split models used in these workflows (LTX-2.3 dev & distilled safetensor, embeddings, audio & video vae & tiny vae):https://huggingface.co/Kijai/LTX2.3_comfy
Gemma - either safetensor or GGUF:
- Gemma 3 12B it safetensor:https://huggingface.co/Comfy-Org/ltx-2/tree/main/split_files/text_encoders
- Gemma 3 12B it GGUF:https://huggingface.co/unsloth/gemma-3-12b-it-GGUF/
Upscale Model
- ltx-2.3-spatial-upscaler (only need the 2x file) - :https://huggingface.co/Lightricks/LTX-2.3/tree/main
LTX-2.3 GGUF models (for GGUF workflows)- one of the source below:
- Quantstack:https://huggingface.co/QuantStack/LTX-2.3-GGUF
- Unsloth :https://huggingface.co/unsloth/LTX-2.3-GGUF
- Vantage :https://huggingface.co/vantagewithai/LTX-2.3-GGUF
Tiny Vae by madebyollin (for sampler previews): (Optional/Recommended. Without this vae you still get previews with latentrgb from KJnodes, at a lower res)
If you are unsure where to put the files seehere
Needed nodes:
- https://github.com/kijai/ComfyUI-KJNodes(NB! Must be up to date for LTX-2 support)
- https://github.com/city96/ComfyUI-GGUF(NB! Must be up to date for LTX-2 support)
- ComfyUI itself must be updated to very latest
LTX-2.3
Lighttricks LTX-2.3 main repro:https://huggingface.co/Lightricks/LTX-2.3 Lightricks LTX-2.3 Collection (loras etc):https://huggingface.co/collections/Lightricks/ltx-23
More workflows :
ComfyUI Official Workflows :https://blog.comfy.org/p/ltx-23-day-0-supporte-in-comfyui
LTX-2 Video Official Workflows :https://github.com/Lightricks/ComfyUI-LTXVideo/tree/master/example_workflows/2.3
For ComfyUI’s new “app mode” some to try here:https://huggingface.co/WanApp
Similar Articles
Lightricks/LTX-2.3-22b-IC-LoRA-LipDub
This Hugging Face model page introduces an IC-LoRA trained on top of LTX-2.3-22b for lip dubbing, with a project page, paper, and inference pipeline available.
TenStrip/LTX2.3-10Eros
This article introduces TenStrip/LTX2.3-10Eros, a fine-tuned AI video model on Hugging Face designed for improved image-to-video generation and prompt adherence. It provides technical details on file formats, compatibility with ComfyUI nodes, and specific prompting strategies for optimal results.
A streamlined Hugging Face model search utility coded by Qwen 3.6-27B
A developer created a streamlined Hugging Face model search utility as a single HTML file with embedded JS, using Qwen 3.6-27B for most of the coding. It organizes models by author, base model, and derivative, with caching to minimize API calls.
Train AI models with Unsloth and Hugging Face Jobs for FREE
Hugging Face and Unsloth are offering free credits and training resources to fine-tune AI models using Hugging Face Jobs, enabling developers to train small language models like LFM2.5-1.2B-Instruct with 2x faster training and 60% less VRAM usage through coding agents like Claude Code and Codex.
Lightricks/LTX-2.3
Lightricks released LTX-2.3, an open-weight diffusion-based audio-video foundation model with improved quality and prompt adherence, available in multiple checkpoints including distilled and LoRA variants for local execution.