Local Video Generation with LTX 2.3 on an RTX 3090

Melvin Vivas · X post · 2026-04-14 · Open on X

Topics: AI Dev Tools & Productivity · Level: intermediate

Summary

The creator runs the LTX 2.3 video model in ComfyUI on a consumer RTX 3090 GPU. Each video takes about 4-5 minutes to generate, and because the model is local you can run unlimited generations for free.

Key points

• Hardware: one RTX 3090 (24 GB VRAM) is enough to run LTX 2.3 video generation.
• Speed: about 4-5 minutes per video.
• Tool: ComfyUI runs the workflow.
• Benefit: unlimited generations with no per-generation cost, unlike cloud video APIs.

Resources mentioned

• LTX 2.3 · tool · huggingface.co · free
  A video generation model from LTX (Lightricks) that makes video from text or images, including start- and end-frame image-to-video, with audio, portrait output and 24/48 fps.
  Also in: Free Local AI Video Generation with LTX 2.3 in ComfyUI (Melvin Vivas on X · notes), AI Video Generation Locally with ComfyUI and LTX 2.3 (Melvin Vivas on X · notes), LTX 2.3 Image-to-Video Running Locally (Demo) (Melvin Vivas on X · notes), Running the LTX 2.3 Open Video Model Locally with ComfyUI on an RTX 3090 (Melvin Vivas on X · notes) and 3 more
• 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

Try this

• Run LTX 2.3 video generation in ComfyUI on a local 24 GB GPU and time how long each video takes