Local Image-to-Video with LTX 2.3 in ComfyUI and Z-Image
Melvin Vivas · X video post · 2026-04-13 · 0:05 · 207 views · Open on X
Topics: AI Dev Tools & Productivity, Industry Trends & Job Market · Level: intermediate
Summary
This is a 5-second demo clip from Melvin Vivas with no narration. It shows a fully local generative-media pipeline: he made a still image on his own machine with the Z-Image model, then animated it with the LTX 2.3 image-to-video model running in ComfyUI. It shows that open models can now handle both image and video generation on local hardware, without cloud APIs.
Key points
- The pipeline has two stages: text-to-image with Z-Image, then image-to-video with LTX 2.3.
- Both stages run locally on the creator's own machine, with no cloud service involved.
- ComfyUI, a node-based workflow tool, is used to run the LTX 2.3 image-to-video model.
- LTX 2.3 is a video model from Lightricks, the company behind LTX Studio. It can animate a single still image into a short clip.
- The post includes no workflow file, settings or hardware details. You'd need to find ComfyUI's LTX workflow templates on your own to reproduce it.
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 2.3 (Lightricks LTX video model) · tool · github.com · free
Lightricks' open video generation model that supports image-to-video and can run locally. - LTX Studio · tool · ltx.studio · check price
A browser-based AI video production platform that now runs on LTX-2.3 and covers the creative workflow from first frame to final delivery.
Also in: Seedance 2.0 Video Model Now Available in LTX Studio (1080p) (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), LTX-2.3 Launch: Fast Native 4K AI Video Generation in LTX Studio (Melvin Vivas on X · notes) - Z-Image · tool · github.com · free
Open text-to-image model that can run on local hardware.
Try this
- Build a fully local generative-media pipeline: generate an image with Z-Image, then animate it with LTX 2.3 in ComfyUI.
More in AI Dev Tools & Productivity
- LTX 2.3 Image-to-Video Running Locally (Demo)
- Free Local AI Video Generation with LTX 2.3 in ComfyUI
- Running the LTX 2.3 Open Video Model Locally with ComfyUI on an RTX 3090
- GLM-5.1 vs Claude Code (Opus 4.6): One-Shot Three.js Racing Game Eval
- Opinion: GPT-5.4 in Cursor 3 Replaces Opus for Coding
- Hot Take: Try Cursor 3 Instead of Claude Code