Running the LTX 2.3 Video Model Locally on an RTX 3090 with ComfyUI

Melvin Vivas · X video post · 2026-03-07 · 0:05 · 247 views · Open on X

Topics: AI Dev Tools & Productivity, Industry Trends & Job Market · Level: intermediate

Summary

This is a short 5-second demo clip with no speech. Melvin Vivas shows the LTX 2.3 video generation model running locally on one consumer NVIDIA RTX 3090 GPU through ComfyUI. The post has no tutorial steps or settings. Its only lesson is that this recent open video model can run on consumer hardware you own, with no cloud API.

Key points

• LTX 2.3, a video generation model from the LTX team (@ltx_model), can run locally on one RTX 3090.
• The RTX 3090 is a consumer GPU with 24 GB of VRAM, so you don't need a data-center card to try it.
• ComfyUI, a node-based interface for running diffusion and generative models, was used to run the model.
• The clip is only a demo. It gives no workflow file, settings, resolution or generation times.
• To reproduce it, follow the official ComfyUI and LTX accounts for workflows and model releases.

Resources mentioned

• ComfyUI · tool · x.com · free
  The official X account for ComfyUI, the node-based tool for generative AI workflows, which announces things like ComfyUI Agent.
  Also in: ComfyUI Agent: early access announcement (Melvin Vivas on X · notes), Comfy Router: One API for Image, Video, 3D and Audio Model Providers (Melvin Vivas on X · notes), Generating AI Video Locally with MiniMax H3 in ComfyUI on an RTX 3090 (Melvin Vivas on X · notes), Running MiniMax M3 Locally in ComfyUI on an RTX 3090 (Melvin Vivas on X · notes) and 23 more
• LTX (@ltx_model) on X · tool · x.com · free
  The official X account of the LTX video model team, with release news and updates.
  Also in: Local AI Video Generation with Audio Using LTX 2.3 (Melvin Vivas on X · notes), LTX 2.3 Image-to-Video Running Locally (Demo) (Melvin Vivas on X · notes), Free Local AI Video Generation with LTX 2.3 in ComfyUI (Melvin Vivas on X · notes)

Try this

• Run the LTX 2.3 video model locally in ComfyUI on a 24 GB consumer GPU such as the RTX 3090.