LTX-2.5 Continuous Audio-Driven Presenter | ComfyUI Workflow
Explore a longer single-shot talking-presenter workflow driven by one portrait and a prepared voice recording.
Included: One editable continuous-shot ComfyUI graph, long-shot planning guide, troubleshooting checklist and input preparation notes.
Requirements: Current ComfyUI, LTX-2.5 local transformer, Gemma projection encoder, LTX video/audio VAEs, latent upscaler and referenced LTX nodes; buyer-supplied portrait and roughly 30-second speech. Substantial VRAM may be needed. Weights and media are not included.
Before buying: this is an editable ComfyUI workflow template, not rendered footage. Long single-shot generation may require lower resolution or duration. The customer version has not been rerendered; no lip-sync accuracy guarantee is made.