LTX 2.3 MSR: Multi-Image Reference Video With Three-Stage Rendering

A developer published a ComfyUI workflow for multi-image reference video generation on LTX 2.3 that uses multi-subject reference (MSR) conditioning to keep subjects distinct rather than blending them into an average face. The workflow adds a three-stage rendering pass — structure, refinement and texture — each with a progressively smaller denoise budget so later stages adjust rather than rebuild, and re-anchors on the reference images between stages to counter the drift that causes a single long pass to lose references midway through a clip. The workflow JSONs are hosted on Hugging Face and require LTX 2.3 models, which are preinstalled on a RunningHub cloud instance.

One workflow for multi-image reference video generation on LTX 2.3, with a three-stage render enhancement pass. You supply a set of reference images and a prompt, and the graph produces a video where the subjects come from the references. MSR multi-subject reference keeps them separate instead of blending them into an average face. Three-stage rendering is applied on top: structure pass, refinement pass, texture pass. Each stage gets a progressively smaller denoise budget so the later stages adjust rather than rebuild. Reference-conditioned video accumulates drift. A single long pass tends to lose the references halfway through. Splitting the render lets you re-anchor on the references between stages, which is what keeps the subject looking like the subject at the end of the clip. ComfyUI export, LTX 2.3 models required. The cloud instance on RunningHub already has them. Workflow JSONs and covers: https://huggingface.co/AI-KSK/ksk-video-262-comfyui-workflows https://huggingface.co/AI-KSK/ksk-video-262-comfyui-workflows Video walkthrough Chinese : https://youtu.be/P-D1niNdJ4w https://youtu.be/P-D1niNdJ4w Bilibili: https://www.bilibili.com/video/BV1xsJw6YEg6/ https://www.bilibili.com/video/BV1xsJw6YEg6/